Nvidia GeForce RTX 3080 Founders Edition Review: A Huge Generational Leap in Performance
Skip to main content
Tom’s Hardware is supported by its audience. When you purchase through links on our site, we may earn an affiliate commission. Here’s why you can trust us.
The GeForce RTX 3080 delivers big gains over Turing and the RTX 2080 Ti, but at a lower price.
Editor’s Choice
(Image: © Tom’s Hardware)
Tom’s Hardware Verdict
Pros
- +
Fastest Graphics Card (until 3090 arrives)
- +
Priced the same as RTX 2080 Super
- +
Delivers true 4K 60+ fps gaming
- +
Runs reasonably cool and quiet
- +
Major architectural updates for future games
Cons
- —
Highest TDP for a single GPU (until 3090)
- —
Potential for CPU bottlenecks
- —
Needs a 1440p or 4K display to shine
- —
We’re not sold on the 12-pin power adapter
- —
No RGB bling (but this is a pro for many!)
Nvidia’s GeForce RTX 3080 Founders Edition is here, claiming the top spot on our GPU benchmarks hierarchy, and ranking as the best graphics card currently available — provided you’re after performance first, with price and power being lesser concerns. After months of waiting, we finally have independent benchmarks and testing data. Nvidia has thrown down the gauntlet, clearly challenging AMD’s Big Navi to try and match or beat what the Ampere architecture brings to the table.
We’re going to hold off on a final verdict for now, as we have other third-party RTX 3080 cards to review, which will begin as soon as tomorrow. That’s good news, as it means customers won’t be limited to Nvidia’s Founders Edition for the first month or so like we were with the RTX 20-series launch. Another piece of good news is that there’s no Founders Edition ‘tax’ this time: The RTX 3080 FE costs $699, direct from Nvidia , and that’s the base price of RTX 3080 cards for the time being. The bad news is that we fully expect supply to be insufficient to keep up with what we expect to be exceptionally high demand.
The bottom line, if you don’t mind spoilers, is that the RTX 3080 FE is 33% faster than the RTX 2080 Ti, on average.
Or, if you prefer other points of comparison, it’s 57% faster than the RTX 2080 Super, 69% faster than the RTX 2080 FE — heck, it’s even 26% faster than the Titan RTX!
But there’s a catch: We measured all of those ‘percent faster’ results across our test suite running at 4K ultra settings. The lead narrows if you drop down to 1440p, and it decreases even more at 1080p. It’s still 42% faster than a 2080 FE at 1080p ultra, but this is very much a card made for higher resolutions. Also, you might need a faster CPU to get the full 3080 experience — check out our companion GeForce RTX 3080 CPU Scaling article for the full details.
- Nvidia GeForce RTX 3080 at Amazon for $959.90
| Graphics Card | RTX 3080 FE | RTX 2080 Super FE | RTX 2080 FE | |
|---|---|---|---|---|
| Architecture | GA102 | TU104 | TU104 | |
| Process (nm) | Samsung 8N | TSMC 12FFN | TSMC 12FFN | |
| Transistors (Billion) | 28. 2)
| 628.4 | 545 | 545 |
| GPCs | 6 | 6 | 6 | |
| SMs | 68 | 48 | 46 | |
| FP32 CUDA Cores | 8704 | 3072 | 2944 | |
| Tensor Cores | 272 | 384 | 368 | |
| RT Cores | 68 | 48 | 46 | |
| Boost Clock (MHz) | 1710 | 1815 | 1800 | |
| VRAM Speed (Gbps) | 19 | 15.5 | 14 | |
| VRAM (GB) | 10 | 8 | 8 | |
| VRAM Bus Width | 320 | 256 | 256 | |
| ROPs | 96 | 64 | 64 | |
| TPCs | 34 | 24 | 23 | |
| TMUs | 272 | 192 | 184 | |
| GFLOPS FP32 | 29768 | 11151 | 10598 | |
| Tensor TFLOPS FP16 (Sparsity) | 119 (238) | 89 | 85 | |
| RT TFLOPS | 58 | 26 | 25 | |
| Bandwidth (GBps) | 760 | 496 | 448 | |
| TDP (watts) | 320 | 250 | 225 | |
| Dimensions (mm) | 285x112x38 | 267x116x38 | 267x116x38 | |
| Weight (g) | 1355 | 1278 | 1260 | |
| Launch Date | Sep-20 | Jul-19 | Sep-18 | |
| Launch Price | $699 | $699 | $799 |
Meet GA102: The Heart of the Beast
(Image credit: Tom’s Hardware)
We have a separate article going deep into the Ampere architecture that powers the GeForce RTX 3080 and other related GPUs.
If you want the full rundown of everything that’s changed compared to the Turing architecture, we recommend starting there. But here’s the highlight reel of the most important changes:
The GA102 is the first GPU from Nvidia to drop into the single digits on lithography, using Samsung’s 8N process. The general consensus is that TSMC’s N7 node is ‘better’ overall, but it also costs more and is currently in very high demand — including from Nvidia’s own A100. Could the consumer Ampere GPUs have been even better with 7nm? Perhaps. But they might have cost more, only been available in limited quantities, or maybe they would have been delayed a few more months. Regardless, GA102 is still a big and powerful chip, boasting 28.3 billion transistors packed into a 628.4mm square die. If you’re wondering, that’s 52% more transistors than the TU102 chip used in RTX 2080 Ti, but in a 17% smaller area.
Ampere ends up as a split architecture, with the GA100 taking on data center ambitions while the GA102 and other consumer chips have significant differences.
The GA100 focuses far more on FP64 performance for scientific workloads, as well as doubling down on deep learning hardware. Meanwhile, the GA102 drops most of the FP64 functionality and instead includes ray tracing hardware, plus some other architectural enhancements. Let’s take a closer look at the Ampere SM found in the GA102 and GA104.
(Image credit: Tom’s Hardware)
Nvidia GPUs consist of several GPCs (Graphics Processing Clusters), each of which has some number of SMs (Streaming Multiprocessors). Nvidia splits each SM into four partitions that can operate on separate sets of data. With Ampere, each SM partition now has 16 FP32 CUDA cores, 16 FP32/INT CUDA cores, a third-gen Tensor core, load/store units, and a special function unit. The whole SM has access to shared L1 cache and memory, and there’s a single second-gen RT core. In total, that means 64 FP32 cores and 64 FP32/INT cores, four Turing cores, and one RT core. Let’s break that down a bit more.
The Turing GPUs added support for concurrent FP32 (32-bit floating point) and INT (32-bit integer) operations.
FP32 tends to be the most important workload for graphics and games, but there’s still a decent amount of INT operations — for things like address calculations, texture lookups, and various other types of code. With Ampere, the INT datapath is upgraded to support INT or FP32, but not at the same time.
If you look at the raw specs, Ampere appears to be a far bigger jump in performance than the 70% we measured. 30 TFLOPS! But it generally won’t get anywhere near that high because the second datapath is an either/or situation: It can’t do both types of instructions on the pipeline in the same cycle. Nvidia says around 35% of gaming calculations are INT operations, which means you’ll end up with something more like 20 TFLOPS of FP32 and 10 TOPS of INT on the RTX 3080.
While we’re on the subject, let’s also point out that a big part of the increased performance comes from increased power limits. RTX 2080 was a 225W part (for the Founders Edition), and RTX 3080 basically adds 100W to that.
That’s half again more power for 70% more performance. It’s technically a win in overall efficiency, but in the pursuit of performance, Nvidia had to move further to the right on the voltage and frequency curve. Nvidia says RTX 3080 can deliver a 90% improvement in performance-per-watt if you limit performance to the same level on both the 2080 and 3080 … but come on, who wants to limit performance that way? Well, maybe laptops, but let’s not go there.
(Image credit: Tom’s Hardware)
One thing that hasn’t changed much is the video ports. Okay, that’s only partially true. First, there’s a single HDMI port, but it’s HDMI 2.1 instead of Turing’s HDMI 2.0b, but the three DisplayPort connections remain 1.4a. And last but not least, there’s no VirtualLink port this round — apparently, VirtualLink is dead. RIP. The various ports are all capable of 8K60 using DSC (Display Stream Compression), a «visually lossless» technique that’s actually not really visually lossless. But you might not notice at 8K.
Getting back to the cores, Nvidia’s third-gen tensor cores in GA102 work on 8x4x4 FP16 matrices, so up to 128 matrix operations per cycle. (Turing’s tensor cores used 4x4x4 matrices, while the GA100 uses 8x4x8 matrices.) With FMA (fused multiply-add), that’s 256 FP operations per cycle, per tensor core. Multiply by the 272 total tensor cores and clock speed, and that gives you 119 TFLOPS of FP16 compute. However, Ampere’s tensor cores also add support for fine-grained sparsity — basically, it eliminates wasting time doing multiplications by 0, since the answer is always 0. Sparsity can provide up to twice the FP16 performance in applications that can use it.
The RT cores receive similar enhancements, with up to double the ray/triangle intersection calculations per clock. The RT cores also support a time variable, which is useful for calculating things like motion blur. All told, Nvidia says the 3080’s new RT cores are 1.7 times faster than the RTX 2080’s, and they can be up to five times as fast for motion blur.
There are plenty of other changes as well. The L1 cache/shared memory capacity and bandwidth has been increased to better feed the cores (8704KB vs. 4416KB), and the L2 cache is also 25% larger than before (5120KB vs. 4096KB). The L1 cache can also be configured as varying amounts of L1 vs. shared memory, depending on the needs of the application. Register file size is also nearly 50% larger (17408KB vs. 11776KB) with the RTX 3080. GA102 can also do concurrent RT + graphics + DLSS (previously, using the RT cores would stop the CUDA cores).
Finally, the raster operators (ROPS) have been moved out of the memory controllers and into the GPCs. Each GPC has two ROP partitions of eight ROP units each. This provides more flexibility in performance, so where the GA102 has up to 112 ROPS total, the RTX 3080 disables two memory controllers but only one GPC and ends up with 96 ROPS. This is more critical for the RTX 3070 / GA104, however, which still has 96 ROPS even though it only has eight memory controllers.
Each GPC also includes six TPCs (Texture Processing Clusters) with eight TMUs (Texture Mapping Units) and a polymorph engine, though Nvidia only enables 34 TPCs for the 3080.
(Image credit: Tom’s Hardware)
With the core enhancements out of the way, let’s also quickly discuss the memory subsystem. GA102 supports up to twelve 32-bit memory channels, of which ten are enabled on the RTX 3080. Nvidia teamed up with Micron to use its GDDR6X memory, which uses PAM4 signaling to boost data rates even higher than before. Where the RTX 20-series cards topped out at 15.5 Gbps in the 2080 Super and 14 Gbps in the other RTX cards, GDDR6X runs at 19 Gbps in the RTX 3080. Combined with the 320-bit interface, that yields 760 GBps of bandwidth — a 70% improvement over RTX 2080.
The RTX 3080’s memory controller has also been improved, with a new feature called EDR: Error Detection and Replay. When the memory detects a failed transmission, rather than crashing or corrupting data, it simply tries again.
It will do this until it’s successful, though it’s still possible to cause a crash with memory overclocking. The interesting bit is that with EDR, higher memory clocks might be achievable, but still result in lower performance. That’s because the EDR ends up reducing memory performance when failed transmissions occur. We’ll have more to say on this in the overclocking section.
(Image credit: Tom’s Hardware)
Nvidia has radically altered the design of its Founders Edition cards for the RTX 30-series. The new design still includes two axial fans, but Nvidia heavily redesigned the PCB and shortened it so that the ‘back’ of the card (away from the video ports) consists of just a fan, heatpipes, radiator fins, and the usual graphics card shroud. Nvidia says the new design delivers substantial improvements in cooling efficiency, while at the same time lowering noise levels. We’ll see the fruits of the design later.
Aesthetics are highly subjective, and we’ve heard plenty of people like the new design, while others think it looks boring.
There’s no RGB bling if that’s your thing, and the only lighting consists of a white GeForce RTX logo on the top of the card with subtle lighting around the ‘X’ on both sides of the card (but only half of the ‘X’ is lit up on the side with the «RTX 3080» logo).
Personally, I think the new card looks quite nice, and it feels very solid in the hand. It’s actually about 100g heavier than the previous RTX 2080 design, and as far as I’m aware, it’s the heaviest single-GPU card Nvidia has ever created. It’s also about 2cm longer than the previous generation cards and uses the typical two-slot width. (The GeForce RTX 3090 is about ready to make the 3080 FE look puny, though, with its massive three-slot cooler.)
Image 1 of 6
(Image credit: Tom’s Hardware)
Image 1 of 6
(Image credit: Tom’s Hardware)Image 1 of 6
(Image credit: Tom’s Hardware)Image 1 of 6
(Image credit: Tom’s Hardware)Image 1 of 6
(Image credit: Tom’s Hardware)Image 1 of 6
(Image credit: Tom’s Hardware)Image 1 of 6
Nvidia provided the above images of the teardown of the RTX 3080 Founders Edition.
We’re not ready to attempt disassembly of our card yet — and frankly, we’re out of time — but we may return to the subject soon. We’re told getting the card apart is a bit trickier this round, mostly because Nvidia has hidden the screws behind tiny covers.
The main board looks far more densely populated than previous GPUs, with the 10 GDDR6X memory chips surrounding the GPU in the center. You can also see the angled 12-pin power connector and the funky-looking cutout at the end of the PCB. Power delivery is obviously important with a 320W TGP, and you can see all the solid electrolytic capacitors placed to the left and right of the memory chips.
The memory arrangement is also interesting, with four chips on the left and right sides of the GPU, up to three chips above the GPU (two mounting positions are empty for the RTX 3080), and a final single chip below the GPU. Again, Nvidia clearly spent a lot of effort to reduce the size of the board and other components to accommodate the new and improved cooling design.
Spoiler: It works very well.
One interesting thing is that the ‘front’ fan (near the video ports) spins in the usual direction — counterclockwise. The ‘back’ fan, which will typically face upward when you install the card in an ATX case, spins clockwise. If you look at the fins, that means the back fan spins the opposite direction from what we normally expect. The reason is that Nvidia found this arrangement pulls air through the radiator better and generates less noise. Also note that the back fan is slightly thicker, and the integrated ring helps increase static pressure on both fans while keeping RPMs low.
If you don’t like the look of the Founders Edition, rest assured there will be plenty of other options. We have a few third-party RTX 3080 cards in for testing, all of which naturally include RGB lighting. None of the third party cards use the 12-pin power connector, either — not that it really matters, since the required adapter comes with the card. Still, that vertically-mounted 12-pin port just looks a bit less robust if you happen to swap GPUs on a regular basis.
I plan to leave the adapter permanently connected and just connect or disconnect the normal 8-pin PEG cables. The 12-pin connector appears to be rated for 25 ‘cycles,’ and I’ve already burned through half of those (not that I expect it to fail any time soon).
TODAY’S BEST DEALS
- 1
Current page:
GeForce RTX 3080 Founders Edition: Hail to the King!
Next Page GeForce RTX 3080: Initial Overclocking Results
Jarred Walton is a senior editor at Tom’s Hardware focusing on everything GPU. He has been working as a tech journalist since 2004, writing for AnandTech, Maximum PC, and PC Gamer. From the first S3 Virge ‘3D decelerators’ to today’s GPUs, Jarred keeps up with all the latest graphics trends and is the one to ask about game performance.
Tom’s Hardware is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site .
©
Future US, Inc. Full 7th Floor, 130 West 42nd Street,
New York,
NY 10036.
Nvidia GeForce RTX 3060 12GB Review: Hope Springs Eternal
Skip to main content
Tom’s Hardware is supported by its audience. When you purchase through links on our site, we may earn an affiliate commission. Here’s why you can trust us.
The GeForce RTX 3060 12GB brings the theoretical price down to just $329, but when will it actually hit that price?
(Image: © Tom’s Hardware)
Tom’s Hardware Verdict
If the GeForce RTX 3060 12GB can come close to its official $329 asking price, it’s a great product for mainstream gamers. But in today’s market, even with reduced mining performance, that’s an unlikely if, as its performance lands right between the RTX 2060 Super and 2070 Super.
Pros
- +
Theoretically great price to performance
- +
Ample 12GB VRAM
- +
Throttled mining to keep it in gamers’ hands
- +
Efficient and compact designs available
Cons
- —
Launch price seems highly improbable
- —
Mining detection of questionable value
- —
Pretty big step down from 3060 Ti performance
- —
EVGA card is a bit noisy
Today’s best EVGA GeForce RTX 3060 12GB XC deals
$406.
99
View
$418.97
View
$1,099
$599.99
View
Reduced Price
Show More Deals
The Nvidia RTX 3060 12GB brings a new level of performance to the mainstream market—sort of. Officially, the RTX 3060 launches today with prices starting at just $329. Realistically? You’re as likely to find one at that price as you are to find an RTX 3060 Ti at $399, RTX 3070 at $499, or RTX 3080 at $699 — not entirely impossible, perhaps, but highly unlikely. Nvidia’s Ampere architecture now powers many of the best graphics cards, and they’re all seeing massive levels of demand from both gamers and cryptocurrency miners.
Nvidia has added firmware and driver code to detect Ethereum mining, which should help a bit, but when people are willing to pay extreme scalper pricing on eBay, even for cards like the GTX 1660 Super and RTX 2060, everything in our GPU benchmarks hierarchy is pretty much sold out right now. Nvidia is even working with partners to bring back previous generation Turing and Pascal cards.
None of that makes this a bad GPU, but we expect the RTX 3060 to be just as difficult to acquire as any other modern GPU. Eventually, the current Ethereum mining boom will fade away, but it could take a year or more before we see the end of chip shortages. That shouldn’t surprise anyone at this point, but if you’ve been hoping for a reasonably priced gaming PC upgrade, it’s a depressing state of affairs.
Image 1 of 9
(Image credit: Tom’s Hardware)
Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
- Nvidia GeForce RTX 3060 12GB at Amazon for $489.
99
Unlike the previous Ampere GPUs, Nvidia won’t offer an RTX 3060 Founders Edition, so we’re looking at a third-party card. Nvidia shipped us the EVGA GeForce RTX 3060 XC for this launch review, a reasonably compact and relatively unassuming card. There’s no metal (or even plastic) backplate, no RGB lighting, and two custom-sized 87mm fans for cooling with a 2.0-slot form factor. The card measures 202x110x38mm and weighs 653g, which is quite the change of pace compared to the other third-party Ampere cards we’ve reviewed so far.
There are reasons for that, of course. Creating a mainstream card and decking it out with all the bells and whistles costs money. And we think most gamers shopping for a good value are far better served by modest designs with good performance. There will certainly be extreme variants of the RTX 3060, and some of them will be priced higher than the budget RTX 3060 Ti options. Let’s be clear: Even the fastest RTX 3060 won’t beat a 3060 Ti in most situations — yes, even with 12GB VRAM.
2)
6Here’s how things break down, comparing the RTX 3060 with its closest Ampere sibling and Turing predecessors. The RTX 2060 and 2060 Super show how much things have changed for the -60 suffix cards between Turing and Ampere. Ampere gives you a lot more shader cores, which means potentially much higher computational performance, and a minor improvement in memory bandwidth for the 12GB card. It also doubles VRAM capacity (at least until the anticipated RTX 3060 6GB shows up, though perhaps maybe Nvidia will just leave that for the RTX 3050 line) and boasts improvements in the RT and Tensor cores, as well as the memory subsystem, all leading to better performance.
Power use remains similar, with a 170W TGP (Total Graphics Power), a decent step down from the RTX 3060 Ti’s 220W TGP.
One interesting tidbit is that this is the first time Nvidia has used 15Gbps GDDR6 memory. The RTX 20-series cards all used 14Gbps memory, except for the RTX 2080 Super that came equipped with 15.5Gbps VRAM. That narrows the bandwidth gap between the 3060 and 3060 Ti a bit, though the extra 64-bits of interface width still gives the GA104 cards a clear advantage. And GA106 doesn’t have an advantage is in ROPs, Render Outputs, as it only has 48 — the same as the RTX 2060.
However, the differences between Turing and Ampere GPUs don’t always show up in specs tables like the above. Theoretically, the RTX 3060 has up to 95% more FP32 performance and 97% more FP16 Tensor core performance than the RTX 2060. In practice, the actual performance difference is much less, as half of the FP32 pipelines share processing resources with INT32 pipelines. The 3060 shouldn’t ever be slower for gaming purposes, but most of the time, it will only be around 20-25 percent faster.
(Image credit: Tom’s Hardware)
This is the first desktop card to use Nvidia’s GA106 processor. At a high level, there are three GPCs (Graphics Processing Clusters), each with up to 10 SMs and 16 ROPs (the two blocks of eight blue rectangles each at the bottom of the GPC). The full chip has 30 SMs while the 3060 disables two and ends up with 28 SMs, but everything else is left alone. (Note that the mobile RTX 3060 has all 30 SMs enabled, though it only comes with 6GB of memory, which is also clocked lower than on the desktop card.)
Each SM contains 64 dedicated FP32 CUDA cores, plus 64 more FP32+INT32 CUDA cores — only FP32 or INT32 can be used for each cycle. The SMs also contain one second-gen RT core and four third-gen Tensor cores, each of which is up to twice the performance as the previous generation cores, and with sparsity the Tensor cores are potentially four times as fast as on Turing. Finally, there are six 32-bit memory interfaces, each one linked to a single 8Gb or 16Gb GDDR6 module — the latter is reserved for desktops at present, with the 8Gb modules used on laptops.
The full GA106 chip has 12 billion transistors, down from 17.4 billion in GA104. That shrinks the die size from 393mm square to just 276mm square, which not only helps to reduce the cost of the chip, but also increases the number of chips Nvidia can get from a single wafer — and if you’re wondering, GA106 is less than half the size of GA102, which measures 628.4mm square and has 28.3 billion transistors. At an estimate, Nvidia can get around 130 dies per wafer with GA104 (some of which are defective, most of which end up as partially disabled chips), while the smaller size of GA106 allows for around 200 dies per wafer. More dies mean better yields and more graphics cards to go around. That’s the hope.
MORE: Best Graphics Cards
MORE: GPU Benchmarks and Hierarchy
MORE: All Graphics Content
- 1
Current page:
Features and Specifications
Next Page EVGA GeForce RTX 3060 12GB XC Teardown
Jarred Walton is a senior editor at Tom’s Hardware focusing on everything GPU.
He has been working as a tech journalist since 2004, writing for AnandTech, Maximum PC, and PC Gamer. From the first S3 Virge ‘3D decelerators’ to today’s GPUs, Jarred keeps up with all the latest graphics trends and is the one to ask about game performance.
Tom’s Hardware is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site .
©
Future US, Inc. Full 7th Floor, 130 West 42nd Street,
New York,
NY 10036.
Nvidia GeForce RTX 3050 Review: Theoretically Mainstream
Tom’s Hardware Verdict
Nvidia’s RTX 3050 delivers good performance for its theoretical $249 starting price. Unfortunately, that also means there’s not a snowball’s chance in hell that it won’t sell for radically inflated prices. It lands between the previous-gen RTX 2060 and GTX 1660 Super, both of which currently sell for far more than Nvidia’s asking price.
Pros
- +
+ Theoretically good price
- +
+ Much better than AMD RX 6500 XT
- +
+ Comes with plenty of VRAM
- +
+ Full PCIe 4.
0 x16 connection
Cons
- —
Little chance it will sell for MSRP
- —
Slower than RTX 2060 and RX 5600 XT
- —
8GB means it can mine crypto
The Nvidia GeForce RTX 3050 feels a bit like a breath of fresh air after last week’s rather unimpressive launch of the AMD Radeon RX 6500 XT. On paper, there aren’t any major compromises to speak of, and the launch price falls squarely into the mainstream market at $249. Unfortunately, GPU prices are still extremely inflated, and while cryptocurrency prices have plummeted, that doesn’t mean we’ll see reasonable prices on the best graphics cards any time soon. But setting aside real-world pricing and supply, how does the RTX 3050 stack up to the competition?
Thankfully, Nvidia hasn’t put the Ampere architecture on the chopping block to create the desktop RTX 3050. While the GA107 used in mobile RTX 3050 Ti and RTX 3050 only uses an x8 PCIe interface, the desktop RTX 3050 uses the larger GA106 chip and includes full PCIe 4. 2)
Along with the RTX 3050, we’ve included the RTX 2060, GTX 1650 Super, and RX 6500 XT as points of reference.
The official launch prices are obviously a bit of a joke right now, with most of these cards costing 50–100% more than the suggested values, but that’s not likely to change any time soon. A key difference between the RTX 3050 and its nominal predecessors, the GTX 1650 and GTX 1650 Super, is that the 3050 adds RT and Tensor cores to the mix. That brings Nvidia’s ray tracing and DLSS support to a new tier of hardware, and like all Ampere GPUs, these are second-gen RT and third-gen Tensor cores.
Of course, that makes performance comparisons between the old and new GPUs sort of pointless in some cases. For example, Nvidia showed how RTX 3050 with RT and DLSS delivered performance compared to the GTX 1650, GTX 1050 Ti, and GTX 1050. So naturally, those GPUs all scored zero in RT and DLSS tests since they can’t run either one. Meanwhile, the GTX 1660 series can support ray tracing (in some games) but still lacks Tensor hardware. So, in effect, every GTX GPU scores zero on RT + DLSS performance, and the same applies to all AMD GPUs.
That’s not a particularly helpful comparison.
One interesting item to note is the die size for the various chips. Nvidia hasn’t revealed a die size for the (currently) laptop-only GA107, but GA106 ends up roughly the same size as the TU116 chip used in the GTX 16-series cards, and 150% larger than AMD’s tiny Navi 24. Some of that is thanks to TSMC’s N6 process, and the cost per square mm for TSMC N6 is certainly higher than Samsung 8N, but die size definitely favors AMD.
At the same time, we’ve already said we think AMD went too far in cutting features and specs to keep the Navi 24 chip as small as possible. Look at all the other specs and RTX 3050 should easily dominate over AMD’s RX 6500 XT, and it might even give the RX 6600 some competition at times. We’ll have the RX 6600 in our performance charts, along with some other current and previous-gen GPUs. One thing to keep an eye on is how the RTX 3050 compares to the RTX 2060. It has quite a bit less bandwidth but also more compute performance.
RTX 2060 will be faster for mining purposes (not necessarily a good thing) as well, which means the RTX 3050 will likely end up in the hands of more gamers going forward.
Obviously, real-world pricing and availability will be the deciding factors for any current graphics card purchase. Nvidia told us it has been working to build up inventory before launching its new GPUs, and it knows the RTX 3050 will be in very high demand thanks to its lower price. It’s still going to sell out, but hopefully we’ll see a decent number of cards available at reasonable prices with tomorrow’s launch. However, once the initial supply gets cleared out, we’ll have to wait and see how things develop going forward.
- AMD Radeon RX 6500 XT at Amazon for $189.99
EVGA GeForce RTX 3050 XC Black
Image 1 of 9
(Image credit: Tom’s Hardware)
Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
(Image credit: Tom’s Hardware)Image 1 of 9
For our launch review, Nvidia provided us with an EVGA RTX 3050 XC Black… except, it sort of didn’t.
Officially, the XC Black runs at reference clocks, meaning a boost clock of 1777MHz. EVGA inadvertently put the non-Black 3050 XC Gaming VBIOS on the card, which gave it a modest factory overclock to 1845MHz boost clock. EVGA did send a corrected VBIOS, and we have now retested everything, but the initial data used the overclocked results.
Fundamentally, we’re not particularly concerned with receiving a factory overclocked card. AMD sent us factory-overclocked RX 6600 XT, RX 6600, and RX 6500 XT cards. Nvidia has also sent some factory overclocked GPUs in the past. The performance difference between the XC Gaming and XC Black should only be about 2–3%, and not surprisingly, the XC Black ran just fine at the XC clocks. You could certainly manually overclock just about any RTX 3050 card to similar levels. If you’re looking at this review and wondering if you should buy the XC Black, the only thing you really need to know is that performance is slightly lower than what we show here, and power consumption is also a tiny bit lower.
The XC Black comes with a suggested starting price of $249, meaning it will likely be available for that price in limited quantities for the launch tomorrow. After the initial launch, all bets are off. We also have a Zotac RTX 3050 Twin Edge OC (1807MHz boost clock), and we’re working on testing that and will post that review in the near future. We have a pricing table in our conclusion that will certainly raise some eyebrows, if you were hoping for more cards selling at the $249 base price.
The RTX 3050 GPU doesn’t require a lot in the way of power or cooling, and as a baseline design, the EVGA XC Black trims most of the extras you’ll find on higher-cost models. There’s no RGB lighting, and the card has two 87mm EVGA fans — it’s essentially identical in appearance to the RTX 3060 EVGA card, except with less VRAM and fewer GPU cores. The card doesn’t include a backplate, but there are still three DisplayPort 1.4a connections and a single HDMI 2.1 port, which is standard for just about every recent GPU introduction other than AMD’s RX 6500 XT.
The card measures 202x110x38mm, only slightly longer than an x16 PCIe slot and also smaller than the XFX RX 6500 XT we reviewed. There’s a single 8-pin PEG power connector that should provide more than enough power for the RTX 3050, and any power from the PCIe slot is just gravy. Interestingly, the XC Black weighs 527g, about 125g lighter than the EVGA RTX 3060. Some of that comes from the two extra memory chips on the 3060, but it also has a slightly reworked heatsink with two fewer copper heatpipes (not that the GPU really needs them).
(Image credit: Tom’s Hardware)
Test Setup for GeForce RTX 3050
TOM’S HARDWARE 2022 GPU TEST PC
Intel Core i9-12900K
MSI Pro Z690-A WiFi DDR4
Corsair 2x16GB DDR4-3600 CL16
Crucial P5 Plus 2TB
Cooler Master MWE 1250 V2 Gold
Cooler Master PL360 Flux
Cooler Master HAF500
Windows 11 Pro 64-bit
As discussed in our Radeon RX 6500 XT review, we’ve recently updated our GPU test PC and gaming suite.
We’re now using a Core i9-12900K processor, paired with a DDR4 motherboard (because DDR5 is nearly impossible to buy and ludicrously expensive right now). We also upgraded to Windows 11 Pro, since it’s basically required to get the most out of Alder Lake. You can see the rest of the hardware in the boxout.
Besides the change in hardware, we’ve also updated our gaming test suite, focusing on newer and more demanding games. While we could include various esports games and lighter fare, we don’t feel that’s particularly useful. Just about any GPU can handle games like CS:GO, for example. Instead, we’re pushing the GPU to its limits to see how the various cards fare.
We’ve selected seven games and test at four settings: 1080p «medium» (or thereabouts) and 1080p/1440p/4K «ultra» (basically maxed out settings except for SSAA). We’ll only test at settings that make sense for the hardware, however, so for example we didn’t test the RTX 3050 at 4K ultra.
We intend to run every card at 1080p medium and ultra, as those will be used for determining ranking in our GPU hierarchy. We’ll also include results with DLSS for the card being reviewed, in games that support the technology.
The games we’re using for the coming year are Borderlands 3, Far Cry 6, Flight Simulator, Forza Horizon 5, Horizon Zero Dawn, Red Dead Redemption 2, and Watch Dogs Legion. Six of the seven games use DirectX 12 for the API, with RDR2 being the sole Vulkan representative. We didn’t include any DX11 testing because, frankly, most modern games are opting for DX12 instead. We’ll revisit and revamp the testing regimen over the coming year as needed, but this is what we’re going with for now.
Along with our standard suite of games, we have a separate suite of games that support ray tracing. We’ll be including performance testing with the same 1080p «medium» and 1080p/1440p/4K «ultra» settings, but with ray tracing enabled — again, where it makes sense for the particular GPU.
Our DXR (DirectX Raytracing) test suite uses the following games: Bright Memory Infinite, Control Ultimate Edition, Cyberpunk 2077, Fortnite, Metro Exodus Enhanced Edition, and Minecraft. We want to provide apples-to-apples comparisons, so we’re testing without DLSS (or FSR or NIS) enabled as our baseline, though on RTX cards like the 3050, we’ll also show performance using DLSS quality mode.
GeForce RTX 3050 Gaming Performance
Please note: Our XC Black came with a boost clock of 1845MHz, not the reference boost clock of 1777MHz. We’ve now included both the original (overclocked) results as «EVGA XCG» along with reference clocked results.
The GeForce RTX 3050 focuses primarily on 1080p gaming, though unlike the RX 6500 XT, it can generally stretch to ultra settings and even manage 1440p at playable (>30 fps) framerates. Naturally, any less demanding games or settings should run even better than what we’ll show in our charts, but we prefer to focus more on a «worst-case scenario» for gaming performance over using games that just about any GPU can run.
We’ll start with our 1080p medium testing.
Image 1 of 8
(Image credit: Tom’s Hardware)
Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
Straight out of the gate, it’s obvious the RTX 3050 performs significantly better than the RX 6500 XT, even at modest settings. It’s a decent step up in performance relative to the GTX 1660 Super as well, which also easily outperformed AMD’s newcomer. (Note that the GTX 1660 Ti and GTX 1660 Super perform nearly identically in all of our previous testing.) The only serious competition will come in the form of higher tier GPUs like the RTX 3060 and RX 6600, though the RTX 2060 and RX 5600 XT also delivered slightly better performance, thanks in no small part to having 192-bit memory interfaces.
Overall, the RTX 3050 averaged 98 fps across our new test suite, at settings that won’t strain the 8GB of VRAM. It was 26% faster than AMD’s RX 6500 XT, 69% faster than the previous generation GTX 1650, and 56% faster than the two-generations-old GTX 1060 6GB, but it only beat the GTX 1660 Super by 6%. At the same time, the RTX 2060 was 9% faster than the RTX 3050, the RTX 3060 beat it by 33%, the RX 5600 XT averaged out to 18% faster as well, and the RX 6600 was 41% faster. (And as a quick side note, the «overclocked» original VBIOS was indeed 2.4% faster overall.)
In other words, the RTX 3050 doesn’t radically change the status quo. If the supply of GPUs was relatively «normal,» the 3050 would slot in just below the three-years-old RTX 2060 6GB. On the other hand, if the supply chain and other factors weren’t happening, this might have been a $199 or $229 card instead of starting at a hypothetical $249.
Naturally, there’s a wider spread in performance when we look at the individual games.
Compared to the RX 6500 XT, the closest AMD got was in Flight Simulator, where the 3050 was only 16% faster. Far Cry 6, Forza Horizon 5, and Red Dead Redemption 2 were all 22–23% faster on the 3050, while the biggest lead was in Borderlands 3, with the 3050 beating the 6500 XT by 44%. That’s largely because Borderlands 3 likes having more memory and memory bandwidth, even when using the 1080p medium preset.
You can also see how much DLSS quality mode improves performance, even at these relatively low settings. HZD was 20% faster, RDR2 improved by 9%, and WDL ran 24% faster. That last result puts the RTX 3050 just behind the RTX 3050 and RX 6600.
Now let’s turn up the heat a bit and see what happens.
Image 1 of 8
(Image credit: Tom’s Hardware)
Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
The RX 6500 XT and other cards with only 4GB VRAM can really struggle at ultra settings in many modern games, but the RTX 3050 continues to perform quite well.
Average performance across our test suite was still 58 fps, though only Far Cry 6 and Horizon Zero Dawn managed to exceed 60 fps. Perhaps more importantly, the RTX 3050 beat AMD’s RX 6500 XT by 53% and increased its lead over other GPUs with 4GB VRAM. Sticking with the current generation «budget» GPU focus, the RTX 3050 was anywhere from 28% faster than the 6500 XT (in HZD) to as much as 95% faster (Forza Horizon 5).
Of course, it’s not all sunshine and roses. Yes, the RTX 3050 can run circles around the RX 6500 XT, but it came in slightly behind the old RTX 2060, and if you’re willing to forego ray tracing hardware, the RX 5600 XT was 14% faster. It also trailed the RTX 3060 by 26%, and the RX 6600 was 36% faster. While it’s not perfect scaling going from the 3050 to the 3060, the 3060 has 50% more memory, 61% more memory bandwidth, and 40% more compute. That works out to 36% higher performance at 1080p ultra.
This isn’t to say that you should run 1080p ultra settings on many of the GPUs in our charts, but at least with the RTX 3050 and faster cards, you can legitimately do so without killing performance.
While running at less than 60 fps isn’t ideal, it’s still definitely playable, and none of the tested games had minimums that consistently fell below 30 fps. DLSS was also able to boost performance by 29% in HZD, 10% in RDR2, and WDL ran 23% faster.
But there’s still a bit of gas in the RTX 3050’s tank…
Image 1 of 8
(Image credit: Tom’s Hardware)
Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
(Image credit: Tom’s Hardware)Image 1 of 8
Okay, 1440p ultra definitely isn’t the sweet spot for the RTX 3050, but while most of the other cards dropped well below 30 fps (1660 Super and above being required to remain «playable»), the RTX 3050 averaged 44 fps.
In fact, it averaged over 30 fps in all seven of the games in our test suite. If you feel like beating a dead horse, it’s also more than twice as fast as the RX 6500 XT this time.
DLSS starts to make even more sense at 1440p ultra, though the gains aren’t any better. HZD performance improved by 21% this time, RDR2 showed its largest gains but still only 12%, and WDL wins out with the biggest improvement so far in our DLSS testing, with 33% higher performance. That was enough to overtake both the RX 5600 XT and RX 6600, and just a few percent behind the RTX 3060 (which of course could run with DLSS as well).
Not counting DLSS, the RTX 3050 is also the slowest of the mainstream graphics cards that we tested. Even at 1440p ultra, the RTX 2060 still eked out a 5% lead, and in the individual game charts, the 3050 only beat the 2060 in Forza Horizon 5 and Watch Dogs Legion, both games that are known to like having 8GB of VRAM or more. The RX 5600 XT was 15% faster as well, the RX 6600 came out 28% ahead, and the RTX 3060 ended up 37% faster than the 3050.
GeForce RTX 3050 Ray Tracing Performance
As an RTX card, ray tracing performance is something to consider, and we tested DLSS on the RTX 3050 as well (in quality mode where applicable, though Minecraft selects its own setting). RT hardware is basically required to run the expanded test suite (GTX 10/16-series cards with 6GB or more VRAM can try to run RT in most of the games in our DXR suite), but with a bit more time, we’ve now managed to collect performance results from some competing GPUs and have charts. (Yay for charts! Who doesn’t love these things?)
As we’ve stated previously, while games with simpler forms of RT that only use one effect (typically shadows) exist, we don’t find the often miniscule visual gains to be worth the performance penalty. In some cases, like Dirt 5, Shadow of the Tomb Raider, and World of WarCraft, it’s hard to tell the difference, even if you’re specifically staring at the shadows. As a result, our RT test suite uses games that all include multiple RT effects.
Incidentally, the RX 6500 XT wouldn’t even let us try to run at our selected RT settings in Control or Fortnite, likely due to only having 4GB VRAM, resulting in a score of «0» for now. The RX 6600 successfully launched Fortnite with our «DXR medium» settings, but it also crashed repeatedly during attempted benchmarking (note that the RX 6600 previously ran Fortnite just fine). We assume there are some driver issues to work out, but we did manage to collect some data for the game.
Image 1 of 7
(Image credit: Tom’s Hardware)
Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
Image 1 of 7
(Image credit: Tom’s Hardware)
Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
(Image credit: Tom’s Hardware)Image 1 of 7
While we tested DXR with both medium and ultra settings, the latter mostly proves too much for the RTX 3050.
Sure, it breaks 30 fps with DLSS in all of the games, but generally speaking, the RTX 3050 hardware is intended for medium to high settings with ray tracing enabled. Therefore, we’ll focus the rest of the discussion on the DXR medium results.
Once again, the RTX 3050 ends up being slightly slower than the RTX 2060, even in ray tracing games. At 1080p medium, the best it can do is a tie in Cyberpunk 2077. That officially makes this the slowest desktop RTX card, by about 7%. But while that might seem bad, you only need to look at the RX 6500 XT, or even the RX 6600, to see just how bad things can get.
The RTX 3050 averaged 40 fps across our demanding DXR test suite at native 1080p. Using the same settings, even if we discount the failed attempts at two of the games, the RX 6500 was still 60–80% slower. In other words, the RTX 3050 was typically more than three times as fast in games with more than a token amount of RT effects.
The RTX 3050 also beat the RX 6600 in DXR performance by 10%, and turning on DLSS only makes things look worse.
DLSS quality mode improved the RTX 3050’s performance by 60% on average (and 70% at our ultra settings), making the RTX 3050 potentially 75–95% faster than the RX 6600. Interestingly, without DLSS, AMD’s RX 6600 did notch one victory in Metro Exodus Enhanced Edition, where it was 10–15% faster.
If you’re at all interested in giving ray tracing games a shot but you want to keep costs as low as possible, the RTX 3050 is a good effort. The RTX 2060 still delivered better performance overall, but it’s certainly possible to get playable framerates in all of the major RT-enabled games, particularly if the game supports DLSS.
(Image credit: Tom’s Hardware)
GeForce RTX 3050 Power, Temps, Noise, Etc.
The GeForce RTX 3050 has an official TDP (board power) rating of 130W. We tested with the original and corrected «reference clocks» VBIOS, but thought it would be interesting to include both results here. We’re using our Powenetics testing equipment and procedures to measure in-line GPU power consumption and other aspects of the cards.
We collect data while running Metro Exodus at 1080p/1440p ultra (whichever uses more power) and run the FurMark stress test at 1600×900. Our test PC remains the same old Core i9-9900K as we’ve used previously, as it’s not a power bottleneck at all.
Image 1 of 4
(Image credit: Tom’s Hardware)
Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
Power usage is one of the RTX 3050’s few disadvantages relative to the RX 6500 XT. The EVGA RTX 3050 averaged 124W of power during the Metro Exodus benchmark loop, compared to just 90W for the 6500 XT. Of course, it also provided substantially better performance, but potentially some PCs with weaker power supplies might benefit — though if that’s the case, we’d recommend upgrading your PSU as well as your GPU. Meanwhile, FurMark’s power use was slightly higher at 134W on average.
Interestingly, the XC VBIOS only made a 3.4W difference in gaming and almost no difference at all in FurMark.
Image 1 of 4
(Image credit: Tom’s Hardware)
Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
Clock speeds for both the reference-clocked VBIOS and the XC VBIOS end up quite a bit higher than the official boost clock, which is typical of Nvidia GPUs. The reference VBIOS still averages 1927MHz throughout the Metro Exodus test, and the XC VBIOS clocked in at 1994MHz, 67MHz higher and almost exactly in line with the difference in official boost clocks (1MHz off). Clock speeds were over 200MHz lower in FurMark, but that’s also expected behavior. The difference in clock speeds between the two VBIOS versions was again almost exactly equal to the difference in boost clock rating — 63MHz this time, compared to the 68MHz difference in specs.
Image 1 of 4
(Image credit: Tom’s Hardware)
Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
Image 1 of 4
(Image credit: Tom’s Hardware)
Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
(Image credit: Tom’s Hardware)Image 1 of 4
The RTX 3050 doesn’t require a ton of power, which means it also doesn’t generate a lot of heat or require high fan speeds. Temperatures maxed out at around 60C for the reference-clocked card, weighed in at 62C for the XC VBIOS in FurMark, and were about 1C lower in Metro Exodus. Fan speeds showed a slightly larger gap, with the reference card sitting at 1818 RPM on average compared to 1918 RPM for the XC VBIOS in Metro. FurMark bumped the fan speed up another 60-70 RPM.
Along with the Powenetics data, we also measure noise levels at 10cm using an SPL (sound pressure level) meter.
It’s aimed right at the GPU fans to minimize the impact of other fans like those on the CPU cooler. The noise floor of our test environment and equipment measures 33 dB(A), and the EVGA RTX 3050 reached a peak noise level of 45.3 dB during testing, with a fan speed of 71%. That’s typical of EVGA’s budget-oriented cards, opting for higher fan speeds with weaker heatsinks and compromising a bit on noise levels. It’s not that the card is loud, but it’s certainly louder than some of the other mainstream cards we’ve tested. We also tested with a static fan speed of 75%, at which point the card generated 48.4 dB of noise, and in warmer environments, it’s entirely possible for the card to exceed that value.
(Image credit: Tom’s Hardware)
GeForce RTX 3050: Good in Theory…
There are two ways to look at the GeForce RTX 3050: How it’s ostensibly supposed to stack up to the competition, and what it looks like in the real world. Let’s start with the former.
The RTX 3050 brings all of Nvidia’s RTX features to a new, lower price point.
Technically, we saw RTX 2060 cards bottom out at around $270 back in the day (from mid-2019 to early 2020), but the lowest MSRP was still $299. However, the 3050’s lower price does come with slightly lower performance, except in a few instances where the extra 2GB VRAM comes into play, at which point the RTX 3050 can basically tie the RTX 2060.
The real saving grace for all of the RTX cards continues to be DLSS. With or without ray tracing, DLSS can provide a nice boost to performance with virtually no loss in image fidelity. We only tested DLSS in our DXR test suite, but it’s also supported in quite a few games that lack ray tracing, like Red Dead Redemption 2, God of War, and many others . AMD’s FSR isn’t really a direct competitor, either. It competes more with Nvidia’s Image Scaling , or at least, Radeon Super Resolution does — it can all get a bit confusing. In short, DLSS quality mode wins out on image quality and does things that FSR, NIS, and RSR can’t.
Maybe Intel’s XeSS will be able to directly compete with DLSS at some point, but DLSS has a significant head start on game developer adoption.
In theory, then, the RTX 3050 looks like a good option. It’s basically the same price as the previous-gen GTX 1660 Super, offers ray tracing and DLSS support (along with Nvidia Broadcast and any other Nvidia technologies that can use the RT or Tensor cores), gives you 2GB more VRAM, and performance is typically 10–15% faster. So if you could buy the RTX 3050 for $249, it’s certainly a reasonable option. Which brings us to the practical aspects of this review.
| Brand | Product Name | Price |
|---|---|---|
| Asus | ROG-STRIX-RTX3050-O8G-GAMING | $489 |
| Asus | DUAL-RTX3050-O8G | $439 |
| Asus | PH-RTX3050-8G | $249 |
| EVGA | XC GAMING | $329 |
| EVGA | XC BLACK GAMING | $249 |
| Gigabyte | GV-N3050GAMING OC-8GD | $379 |
| Gigabyte | GV-N3050EAGLE OC-8GD | $349 |
| Gigabyte | GV-N3050EAGLE-8GD | $249 |
| MSI | RTX 3050 Gaming X 8G | $379 |
| MSI | RTX 3050 Ventus 2X 8G OC | $349 |
| MSI | RTX 3050 Aero ITX 8G | $249 |
| Zotac | Twin Edge OC | $399 |
| Zotac | Twin Edge | $249 |
The GeForce RTX 3050 officially goes on sale tomorrow, January 27.
We’ve already seen advance listings pop up with prices that are nowhere near the «recommended» $249, and in some cases, prices are $400 or more. We’ll see how things shake out over the coming weeks and months, but when the GTX 1660 Super has a current average selling price of $475 on eBay during the past week — and that’s after the recent drop in GPU prices that we’ve noticed — there’s little reason to expect the RTX 3050 to sell at substantially lower prices. If the miners don’t nab them, the bots and scalpers probably will.
You can see the above table of «official» launch prices from Nvidia’s various add-in card partners. Every one of them has a card with a $249 price point, but the jump from there to the overclocked cards ranges from as little as $80 for the EVGA XC Gaming to a whopping $240 gap for the Asus Strix card. Considering EVGA inadvertently proved there’s little difference between the XC Gaming and XC Black other than the VBIOS, you probably don’t want to spend a ton of extra money on the typically modest factory overclocks.
For Nvidia’s partners, it’s clear that if they can successfully overclock a chip and sell it for more money, they would much rather sell a $349 or $489 card than a $249 model in a market where every card gets sold. We’ve seen this in the past, like the EVGA RTX 2080 Ti Black that was one of the few 2080 Ti cards with an official price of $999. They were almost never in stock, and most 2080 Ti models sold at $1,199 or more (the Founders Edition’s price).
Fundamentally, it all goes back to supply and demand. Even if the RTX 3050 isn’t great for mining — and in the current market, it most certainly isn’t, averaging just 22MH/s in Ethereum, which would net a mere $0.60 per day at current prices — there are far too many other people looking to upgrade their PCs. The supply of the RTX 3050 at launch might be okay (it will still sell out in minutes), but it still uses the same GA106 chip as the RTX 3060, and we don’t expect long-term supply to be any better than that card. As with the AIC partners, why would Nvidia want to sell GA106 chips in a nominally $249 card if it can put those same chips into a $329 card?
Given that the performance generally ends up being worse than the RTX 2060 and RX 6600, those cards should represent a practical ceiling on RTX 3050 prices.
That doesn’t bode well since both of those currently average around $510 on eBay. How much should you actually pay for an RTX 3050, if you’re interested in buying one? That depends in part on how badly you need it, but we’d try to keep things under $350 as an upper limit. If you can’t find the card for less than that, you should probably just wait.
Whatever you choose to do, let’s also not forget that Ada Lovelace (we’ve heard it referred to by both the first and last name), a.k.a. the RTX 40-series, will likely land this fall. Nvidia will probably start with the top-tier parts like the RTX 4090 and 4080 rather than looking at the budget and mainstream parts, but AMD is also working on RDNA3. With both slated to use TSMC’s N5 process, supply may or may not be any better than the current GPUs, but we expect a decent performance jump. Depending on where prices go between now and the fall, sitting out the current generation of GPUs isn’t a bad idea at this stage.
MORE: Best Graphics Cards
MORE: GPU Benchmarks and Hierarchy
MORE: All Graphics Content
Jarred Walton is a senior editor at Tom’s Hardware focusing on everything GPU.
He has been working as a tech journalist since 2004, writing for AnandTech, Maximum PC, and PC Gamer. From the first S3 Virge ‘3D decelerators’ to today’s GPUs, Jarred keeps up with all the latest graphics trends and is the one to ask about game performance.
Nvidia GeForce RTX 3080 Founders Edition review
Our Verdict
The new Nvidia card houses a monster of a GPU, tearing up the Turing generation and making ray traced gaming worthwhile. And this Founders Edition is the ultimate expression of the GeForce RTX 3080.
For
- Incredible gen-on-gen fps boost
- Makes 2080 Ti look mid-range
- Ray tracing isn’t a sacrifice
Against
- Needs a beefy PSU
Today’s best Nvidia GeForce RTX 3080 deals
£1,154.99
£1,099.90
View
Reduced Price
£1,512.
99
£1,201.02
View
Reduced Price
£1,257.85
View
Show More Deals
It feels almost redundant to call the new Nvidia GeForce RTX 3080 the fastest graphics card you can buy. I mean, today, it absolutely is, and after the first reveal that was pretty much inevitable. The initial performance figures from the green team’s grand unveiling were no joke: this thing takes the RTX 2080 Ti outside and gives it a good, sound kicking. It’s not even close.
The ol’ Turing GPU’s now whimpering in the corner, its vapour chambers leaking out over my floor as its fans fitfully spin their last.
Which is a pretty spectacular result when you consider the top-end Turing chip was the previous holder of the ‘fastest graphics card’ title, with its bold specs list and $1,200 sticker price.
The fact this $699 card can make such a performance step up, at the same price as the RTX 2080 Super it’s replacing, is incredible.
It’s at once testament to the new Nvidia Ampere architecture, the work its engineers have put in, and maybe to the more competitive landscape of 2020.
The GeForce RTX 3080 is the flagship graphics card of this new Ampere generation. At least that’s what Jen-Hsun and Co. is calling it, despite the GeForce RTX 3090, with a superior specs list, launching very, very soon. But that’s a $1,500 GPU, and however much you might want the borderline offensive power the RTX 3090 is promising, the RTX 3080 is the far more realistic option for those of us without a Hollywood bank balance.
So, how has Nvidia managed to not just deliver RTX 2080 Ti levels of gaming performance, but fly past it at an unprecedented rate of knots? It’s a mixture of smart design choices, a whole bunch more transistors, and some serious engineering.
Specifications
(Image credit: Future)
Nvidia GeForce RTX 3080 specs
The key specs, most especially when it comes to gaming, are those heavily beefed up CUDA core numbers.
We’re seeing effectively twice the number of cores compared to what we were expecting, and far more than the equivalent GPU of the previous Turing generation. That’s down to the redesigned data paths Nvidia has fitted into the GA102 silicon at the heart of the RTX 3080.
The full GA102 GPU, the same essential chip which powers both the RTX 3080 and the upcoming RTX 3090, houses 10,752 CUDA cores. The cut-down version dropped into the RTX 3080, however, sports 8,704. That is still a huge increase over the paltry 3,072 CUDA cores Nvidia released the RTX 2080 Super with just last year. Although that kinda depends on your definition of a ‘core’.
These cores are arrayed across 68 streaming multiprocessors (SMs), which means that you get a few more of the dedicated 2nd gen RT Cores too. Because of the way the new architecture is designed, however, you do get fewer AI-driving Tensor Cores.
Image 1 of 2
Full GA102 GPU (Image credit: Nvidia)
Image 1 of 2
RTX 3080’s cut down GA102 GPU (Image credit: Nvidia)Image 1 of 2
RTX 3080 specs
GPU — GA102
Lithography — Samsung 8nm
Die size — 628.
4mm2
Transistors — 28.3 bn
CUDA cores — 8,704
SMs — 68
RT Cores — 68
Tensor Cores — 272
GPU Boost clock — 1,710MHz
Memory bus — 320-bit
Memory capacity — 10GB GDDR6X
Memory speed — 19Gbps
Memory bandwidth — 760GB/s
TGP — 320W
The GeForce RTX 3080 GPU is built on the Samsung 8N design, which is nominally an 8nm production node, with a die size of 628.4mm2. That’s smaller than the top Turing chip, which was 754mm2, but packs in another 10 billion transistors at 28.3 billion transistors. It is though a larger slice of silicon than the TU104 which powered the equivalent level card of the last generation, the RTX 2080.
A side-by-side look at the Boost clock speed of the RTX 3080 compared with the RTX 2080 Super might have you worrying for the performance of the GPU as it rated slower, but in our testing we’ve clock speeds well north of 1,800MHz as standard—at a similar level to the last-gen Turing card.
You do get faster memory too, with 10GB of GDDR6X memory, running across an aggregated 320-bit memory interface. That delivers a pretty spectacular 760GB/s of bandwidth compared with the sub-500GB/s of the standard GDDR6 of the Turing card.
But you are definitely going to need some serious PSU performance for your new card, because this Founders Edition has a board power rating of 320W, and we’ve seen this version of the RTX 3080 running well above that on average, with peaks up to 368W in demanding games.
Nominally Nvidia is suggesting a 750W PSU as a minimum, but that’s not really taking into account the higher power draws of some modern CPUs. If you’re rocking a Core i9 10900K , for example, you’ll likely need 850W at least.
Thankfully the innovative cooling solution on the RTX 3080 Founders Edition is definitely up to the task. It’s a big, dense mountain of vapor chambers and direct contact heatpipes, which helps the card maintain those clock speeds way above the rated Boost numbers.
Image 1 of 3
(Image credit: Nvidia)
Image 1 of 3
(Image credit: Nvidia)Image 1 of 3
(Image credit: Nvidia)Image 1 of 3
The PCB itself is a custom design, one we’re not seeing on third-party cards, at least not yet anyways. It’s a surprisingly compact board, with all the necessary componentry squeezed into a small space to allow for a cutout to enable the second chill spinner to do its job.
The throughflow design of this secondary fan pulls air across the cooling block, giving additional chip-chilling capabilities alongside the direct fan sat atop the GPU itself. The idea is that one vents out the back of the graphics card and the other out the back of the PC.
My only concern with this design is that you might end up getting toasted air circulating around your CPU’s air-cooler in a traditional mounting, which could affect processor temperatures. Nvidia maintains that it would have no impact at all, and if you’re rocking an all-in-one liquid cooler it’s definitely not going to matter.
Architecture
(Image credit: Nvidia)
Nvidia GeForce RTX 3080 architecture
The new SM design, and therefore the core-count, is one of the key differentiators between the Turing and Ampere GPU architectures. When Nvidia talks about its GPU cores, it’s referencing 32-bit floating point (FP32) units. Most graphics workloads are based on floating point operations (at the launch of Turing Nvidia claimed that for every 100 FP instructions there were 36 integer pipe instructions), and so doubling the number of available units massively accelerates most gaming tasks.
In Turing Nvidia made FP32 and INT workloads concurrent, meaning parts of the GPU weren’t twiddling their silicon thumbs waiting for one or the other type of task to be completed before getting on with its own thing. «Before Turing [the GPU] was only able to really issue one math instruction per clock,» explains Jonah Alben, senior VP of GPU engineering at Nvidia, «and we found that was holding back performance in a lot of cases.
«
Like Turing, there are still two data paths in the Ampere design, but while previously they were split down the line between integer and floating point operations—concurrent though they were—Ampere now allows FP32 workloads on either data path.
(Image credit: Nvidia)
«Now it’s an FP32-plus-integer unit that has enabled us to double up our performance on those floating point heavy workloads,» Alben tells us. «So now we have amazing performance for that kind of workload, like denoising and other image processing workloads you’ll see in a game engine.»
Nvidia’s streaming multiprocessors (SMs) are split into four partitions, each with a dedicated FP32 data path, but in Ampere the second path offers both integer and FP32 operations. That means there is potentially twice the number of FP32 units available, though given there will still be times where that second data path has to be running integer operations you’re not always getting twice the floating point performance.
Nvidia has also beefed up the cache around the enhanced data paths because, as Alben explains «feeding that, of course is always a challenge. The faster these processors go, the more it actually matters that they have a lot of bandwidth to be fed. And this was more of a significant architectural change where we basically replumbed the pipeline to our L1 cache system so that now has double the bandwidth.»
With modern game engines, however, especially moving into this next-generation of gaming, it’s not just about floating point or integer operations. With real-time ray tracing set to become ever more prevalent in games, thanks to the new Sony and Microsoft mini PCs launching this year, Nvidia has taken the opportunity to update the RT Cores first introduced in the Turing RTX GPUs.
At its most basic, the RT Core is a specific fixed function unit dedicated to accelerating the bounding volume hierarchy (BVH) algorithm at the heart of ray tracing workloads. It’s a workload unlike anything else you do in a shader core, so it’s very inefficient to try and run them on a standard GPU.
Just look at how well the GTX 1080 deals with ray tracing for a hint…
There are two parts to this dedicated ray tracing core, one that sorts the bounding boxes, and another which then traces triangle intersection rates for the different rays. But the first-gen RT Core is by no means the finished product.
«We found that we had really good bounding box intersection rates,» says Alben, «but the triangle intersection rates at the end of the tracing could be a bottleneck.»
(Image credit: Nvidia)
So now the RT is able to do more in parallel; so for some rays it will be tracing the bounding boxes while it will be calculating the triangle intersections for others.
«So we have separate resources for these two units, they can run in parallel, and the triangle side has double the performance of the last time.»
This added parallelism, as well as a new way to trace triangles through time and space to speed up the calculation of motion blur effects in ray traced scenes, means there is genuine acceleration of ray tracing performance on the whole.
Pick your expletive, because the RTX 3080 Founders Edition is ****ing great
The third piece of the Ampere GPU puzzle is the 3rd gen Tensor Core. This is purely a slice of silicon dedicated to deep learning and AI, but before you scan down to the score and snappy summation at the end, it really is relevant to gaming. It’s the part of the GPU which is responsible for DLSS, or deep learning super sampling, or ‘that bit of magic that makes ray traced games actually playable’.
In a bit of a switcheroo there are actually fewer Tensor Cores per SM than with Turing. «We found that it was actually better to have a smaller number of cores per SM,» Alben explains, «and then make each core much more powerful than the previous generation.»
The basic performance of the Tensor Core has been doubled in Turing, but Nvidia is also using ‘Sparse Deep Learning’ to make the whole process more efficient. It’s basically a way of pruning away a bunch of maths that isn’t really necessary for the final outcome, and that seriously accelerates the performance of DLSS 2.
0. And DLSS 2.1 when it comes too.
Nvidia is also introducing DLSS 8K , which leverage a new 9x super resolution scaling factor with the aim of bringing 60fps gaming within reach at 8K resolutions, even on ray tracing enabled games. Damn. But that’s not exactly within reach of the RTX 3080 itself and is more set out for the upcoming RTX 3090, the card Nvidia is calling the «world’s first 8K HDR gaming GPU.»
Minecraft with RTX and DLSS (Image credit: Mojang)
But then there’s the new memory sub-system which is relevant to the RTX 3080. Working with Micron, and the DRAM industry at large, Nvidia has helped create a new higher speed version of GDDR6, catchily titled, GDDR6X. Using some snazzy new signalling inside this new memory type GDDR6X is able to shift more data around and do it at faster rates. Today’s data-hungry game engines, especially those keyed into ray tracing workloads, ought to thrive on the newer memory tech.
It’s complicated stuff, but all you really need to know is that it’s fast, like 19Gbps fast on the GeForce RTX 3080.
That all means there’s a huge amount of memory bandwidth available to the Ampere card, with 760GB/s on the RTX 3080 vs. 496GB/s on the RTX 2080 Super.
What else is rather complex is the RTX IO feature wrapped up in the new RTX 30-series design. These new Nvidia Ampere GPUs support Microsoft’s DirectStorage API, one of the most exciting features coming to next-gen consoles . And this means that Nvidia is almost taking the CPU out of the equation when it comes to decompressing the huge high-fidelity, high-resolution scenes that will fill out next-gen games.
But we’re not expecting RTX IO enabled games to arrive until well into next year, so right now this is a bit of a dormant feature of the RTX 3080. Though, as the competition is want to say, that ought to mean the Ampere architecture ages like fine wine as the next generation of gaming rolls along.
(Image credit: Nvidia)
What can make a difference today, however, is Nvidia Reflex . This is a feature being baked into some of the top esports games of today, such as Fortnite, Apex Legends, and Valorant, and is aimed at providing an SDK which allows devs to drop settings into their games to reduce system latency when you hit GPU-intensive scenes.
In a similar way to how G-Sync synchronises the GPU with the monitor, Reflex does the same between CPU and GPU with the result being that there are never frames waiting in the render queue. It also allows games to sample the individual mouse click at the very last second to get the input lag down as much as possible.
Reflex needs to be enabled at a game level however, but it also partners up with GSync. There’s a new module going into the latest 360Hz gaming displays from Asus, and its ilk, which includes the Reflex Latency Analyser, and that allows you to measure mouse, display, and full system latency without the need for specialist equipment. Well, apart from an expensive new 360Hz panel anyways.
That won’t cut latency itself, but might help you figure out what the bottleneck is on your system. Or at least come to the conclusion that bottleneck is, well, you.
Benchmarks and performance
(Image credit: Future)
Nvidia GeForce RTX 3080 benchmarks and performance
You should know how this is going to go by now.
The RTX 3080 is an absolute monster of a gaming GPU, and is able to deliver frame rates which make the $1,200 RTX 2080 Ti look like a thoroughly mid-range graphics card.
At the lowest 1080p resolution levels you are only getting a modest performance bump over the Ti, but that’s when you’re talking about frame rates getting into the 200+ level. At that point it’s less about graphics power and more about the rest of the system. Dropping in a chunk more FP32 cores ain’t going to do a lot there.
Image 1 of 9
(Image credit: Future)
Image 1 of 9
1080p benchmarks
(Image credit: Future)
Image 1 of 9
1080p benchmarks
(Image credit: Future)
Image 1 of 9
1080p benchmarks
(Image credit: Future)
Image 1 of 9
1080p benchmarks
(Image credit: Future)
Image 1 of 9
1080p benchmarks
(Image credit: Future)
Image 1 of 9
1080p benchmarks
(Image credit: Future)
Image 1 of 9
1080p benchmarks
(Image credit: Future)
Image 1 of 9
1080p benchmarks
(Image credit: Future)
Image 1 of 9
1080p benchmarks
But when you shift gears into 1440p and 4K resolutions, however, especially in the more demanding game engines, that’s when the RTX 3080’s performance chops really come to the fore.
When the going gets tough I’ve been seeing frame rates jumps of between 25 percent and 43 percent over the RTX 2080 Ti.
You can now get higher ray traced frame rates than the previous generation could offer without it
That’s a huge performance uplift over the absolute top-end of not just the previous generation of Nvidia graphics cards, but what was the absolute fastest consumer GPU ever made. And when you consider the RTX 3080 isn’t even the most performant of the new Ampere generation you can see what the architectural changes have done for the gaming prowess of the new GeForce cards.
According to Nvidia we shouldn’t really be talking about its comparative performance with the Ti because that’s not really the card the RTX 3080 is replacing. That’s the RTX 2080 Super, and here it’s even worse news for people who dropped the best part of a grand on a new GPU over the last 12 months. Coming in at the same $699 sticker price as the RTX 2080 Super was launched at, the RTX 3080 destroys it.
Image 1 of 9
(Image credit: Future)
Image 1 of 9
1440p benchmarks
(Image credit: Future)
Image 1 of 9
1440p benchmarks
(Image credit: Future)
Image 1 of 9
1440p benchmarks
(Image credit: Future)
Image 1 of 9
1440p benchmarks
(Image credit: Future)
Image 1 of 9
1440p benchmarks
(Image credit: Future)
Image 1 of 9
1440p benchmarks
(Image credit: Future)
Image 1 of 9
1440p benchmarks
(Image credit: Future)
Image 1 of 9
1440p benchmarks
(Image credit: Future)
Image 1 of 9
1440p benchmarks
But where Nvidia has been talking about performance up to twice that of the original RTX 2080 that is only in a few very specific titles. In my testing only Shadow of the Tomb Raider presents such a situation, but still doubling the 4K frame rates of the Super is hugely impressive.
That said, the uplift is still significant over the previous generation across the board: my 1440p gains average out at 50 percent faster frame rates and the 4K performance boost is even higher at 65 percent on average.
Image 1 of 10
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
(Image credit: Future)
Image 1 of 10
4K benchmarks
The accelerated second-gen RT Cores are very much in play when you check out the relative ray traced performance of the Turing and Ampere cards. All you really need to know is that you can now get higher ray traced frame rates than the previous generation could offer without the feature turned on. That highlights just where this new architecture has moved the game on in that regard.
Basically, it is safe to go RTX on in-game now.
Image 1 of 7
(Image credit: Future)
Image 1 of 7
Ray tracing benchmarks
(Image credit: Future)
Image 1 of 7
Ray tracing benchmarks
(Image credit: Future)
Image 1 of 7
Ray tracing benchmarks
(Image credit: Future)
Image 1 of 7
Ray tracing benchmarks
(Image credit: Future)
Image 1 of 7
Ray tracing benchmarks
(Image credit: Future)
Image 1 of 7
Ray tracing benchmarks
(Image credit: Future)
Image 1 of 7
Ray tracing benchmarks
Nvidia has also been keen to talk a lot about the performance per Watt gains the Samsung 8N process, and Ampere architecture efficiencies, have enabled it to drop into the RTX 30-series. And honestly I think a lot of that pre-launch noise is because these are still incredibly thirsty graphics cards. The peak Wattage I’ve got out of this Founders Edition card, with its innovative PCB and 12-pin PSU connector is 368W, well over the rated 320W TGP Nvidia has been touting.
On average, however, I’m seeing board power of 324W, which sits more in line with the specifications, but is still a hell of a lot of PSU juice.
Yet it is still a more efficient GPU than the card it’s replacing, and the top RTX 2080 Ti too. Considering Turing was already a pretty efficient architecture in its own right that’s an impressive feat.
In the real world, with the Ampere GPU left to its own devices, chowing down on as much power as your PC can give it, you’re only looking at around 19 percent higher performance per Watt compared with the RTX 2080 Super. That’s at 4K, and the delta almost vanishes lower down the resolution scale. At 1080p it’s just 2 percent.
Image 1 of 3
(Image credit: Future)
Image 1 of 3
Thermals and power
(Image credit: Future)
Image 1 of 3
Thermals and power
(Image credit: Future)
Image 1 of 3
Thermals and power
Test rig
CPU — Intel Core i7 10700K
Motherboard — MSI MPG Z490 Gaming Carbon WiFi
RAM — Corsair Vengeance RGB Pro @ 3,200MHz
CPU cooler — Corsair h200i RGB Pro XT
PSU — NZXT 850W
Chassis — DimasTech Mini V2
Monitor — Philips Momentum 558M1RY
Nvidia has been boasting of a 1.
9x perf/W boost over Turing, however, but you can only see that in situations where the previous generation is really pushing its hardest. The green team has shown when the RTX 2080 is maxing out at 55fps with all the bells and RTX whistles enabled in Control, the RTX 3080 is almost twice as efficient. But that’s an outlier.
We’ve capped both the RTX 2080 Super and the RTX 3080 at 60fps at 1440p in a variety of titles and then the perf/W delta is again a lot smaller. That is until you get to ray traced benchmarks—at that point the redesigned RT Cores and extra FP32 units come into play and you see a far more significant boost in efficiency. In Shadow of the Tomb Raider and Metro Exodus, with ray tracing set to Ultra, you get 38 percent and 46 percent higher perf/W respectively.
And how does that new chip-chiller perform? Remarkably well. Remember those days of your reference card cooler maxing out at 90°C and that being fine? Well, no more. The RTX 3080 peaks at around 75°C in my testing, and averages out at 68°C, despite that huge amount of power flooding through the system.
It’s not loud either, even when you really push the card. Plus it’s got the 0dB fan feature, which means they don’t even start spinning until you top the mid sixties in terms of temps.
We’ll have to see how well it deals with overclocking, however, because I’m still waiting on release drivers and the new OC tools to really get to grips with that. Right now it’s just not stable operating much above its standard clock speed.
Verdict
(Image credit: Future)
Nvidia GeForce RTX 3080 verdict
Pick your expletive, because the RTX 3080 Founders Edition is ****ing great. Far from just being the reference version of the ‘flagship’ Ampere graphics card, because of that cooler and redesigned PCB, it is the ultimate expression of the RTX 3080. And if you end up with another version of this fine-ass GPU then I’m afraid you’re likely to feel a little hard done by.
And chances are you might have to make do. The Founders Edition cards are not going to be produced in the same volumes as the third-party versions from the likes of Asus, Palit, and Colorful, to name but the few we’ve seen.
This is a whole new generation of card, it’s seriously good, and that means stock will likely vanish of the RTX 3080 FE almost as soon as it’s launched, and may take a while to return and level out.
But I’d probably suggest you wait, because I think it’s worth it for such a good-looking, impressively performant version of the Ampere GPU. It might not necessarily be the coolest, looking at the vast heat-sinks on some of the AIB offerings, but it’s probably the one I’d be happiest having in my rig.
The extreme power demands are interesting however, and likely a stick that the competition will want to use to beat Ampere with. Though I would wager any concerns aren’t going to sway the average gamer away from picking Ampere for their powerful new GPU. If you want to be particularly green about the power you use gaming then you’re not running a desktop PC with a high-end discrete graphics card.
The performance uplift you get over the previous generation is huge, and almost unprecedented.
Maybe we’ve become used to more iterative generational deltas, especially considering the slight difference between the GTX 1080 Ti and RTX 2080, for example. And we’re going to continue beating the Ti drum, because it bears repeating—the fact the $699 RTX 3080 can absolutely smash the $1,200 RTX 2080 Ti is rather staggering.
(Image credit: Future)
Of course that maybe says a lot about the market right now compared with two years ago. Back then there was nothing the competition could produce to go up against even the GTX 1080 Ti, but with the AMD RX 6000 on the horizon at the end of October, and suggested to be a fair bit faster than the ol’ RTX 2080 Ti, Nvidia couldn’t have gone for a minor performance update this time around.
There is potentially more competition in the high-end GPU space again, and with the RTX 30-series lineup announced so far it looks like the green team is going for some shock and awe tactics ahead of the upcoming Radeon launch. So, thanks AMD for pushing Nvidia, because we’re getting some great cards being released to loom over Big Navi.
Jen-Hsun and Co. has gone big with the RTX 3080, and the result is an outstanding gaming card that sets a new benchmark for both high-end 4K gaming performance and for ray tracing. And honestly that has us salivating over the potential of both the $499 RTX 3070 and the ludicrous potential of the $1,500 RTX 3090.
Read our review policy
Nvidia GeForce RTX 3080
The new Nvidia card houses a monster of a GPU, tearing up the Turing generation and making ray traced gaming worthwhile. And this Founders Edition is the ultimate expression of the GeForce RTX 3080.
Dave has been gaming since the days of Zaxxon and Lady Bug on the Colecovision, and code books for the Commodore Vic 20 (Death Race 2000!). He built his first gaming PC at the tender age of 16, and finally finished bug-fixing the Cyrix-based system around a year later. When he dropped it out of the window. He first started writing for Official PlayStation Magazine and Xbox World many decades ago, then moved onto PC Format full-time, then PC Gamer, TechRadar, and T3 among others.
Now he’s back, writing about the nightmarish graphics card market, CPUs with more cores than sense, gaming laptops hotter than the sun, and SSDs more capacious than a Cybertruck.
Nvidia RTX 3060 Ti review Founders Edition
Skip to main content
PC Gamer is supported by its audience. When you purchase through links on our site, we may earn an affiliate commission. Here’s why you can trust us.
The RTX 3060 Ti is more than a replacement for the RTX 2060 Super, instead it faces down the $699 RTX 2080 Super—and wins.
(Image: © Nvidia)
Our Verdict
The RTX 3060 Ti is exactly what we expected from a fourth-tier RTX 30-series graphics card, but that’s no mark against it. Nvidia’s Ampere cards offers an almost unprecedented leap in gaming performance over past generations, and the RTX 3060 Ti manages to deliver more of the same on a slimmer budget.
For
- 4K performance
- Most affordable Ampere
- Decent ray tracing performance
- Great cooler
Against
- Inventory is sure to be tight
- AMD’s potential retort
The Nvidia RTX 3060 Ti may come as a surprise considering its launch ahead of a standard, non-Ti RTX 3060.
Or it would have if word of its arrival hadn’t been plastered across the internet for months now. Yet even if it breaks convention, it is nonetheless a welcome addition to the RTX 30-series lineup: as a sub-$400 card, it’s a far more affordable Ampere graphics card that its forebears.
The cheapest of the lot up until now has been the Nvidia RTX 3070 , and while being a great card for 1440p and 4K gaming it still necessitates a considerable chunk of change by way of its $499 (£469) price tag. The RTX 3060 Ti goes some some way to dropping required pay-grade for Ampere at $399 (£369).
Of course its closest match remains the RTX 3070, and its similarity to the bigger sibling runs deeps. Both use a matching memory loadout—8GB of GDDR6—and make use of the same GPU at their core, namely the GA104, fabricated on Samsung’s 8nm process. The RTX 3060 Ti delivers a slightly cut-down payload of 4,864 CUDA Cores divided across 38 SMs, compared to the 5,888 cores and 46 SMs within the RTX 3070—a 17% reduction in graphics-chomping silicon.
That also makes for fewer RT Cores and Tensor Cores, although as you’ll see in our benchmarking that doesn’t make the RTX 3060 Ti any less a ray tracing card in its own right. These are 2nd generation RT Cores and 3rd generation Tensor Cores, and we’re seeing a notable improvement over those included with the Turing architecture and the RTX 20-series.
And it’s exactly a comparison with the RTX 20-series lineup that Nvidia is hoping for. While priced the same as the RTX 2060 Super, the RTX 3060 Ti is aimed squarely at the performance of the second-run RTX 2080 Super . This is a $399 card facing down what was a $699 graphics card at launch. While that’s no longer a graphics card you can really buy—nor can you really purchase any card whatsoever at the time of writing—the RTX 3060 Ti clearly offers a more performant and affordable alternative.
There’s undoubtedly a not-too-distant competitor to the RTX 3060 Ti on the way from AMD, too. We’d suppose that’s bound to look RX 6700-shaped and offer performance upwards of the $399 RX 5700 XT—it’s certainly not impossible to picture such a card out of the red team, either, given what we know about RDNA 2 today.
But that’s a comparison for another day given the struggles AMD has similarly had getting any actual GPU stock out in front of its fans. For now the RTX 3060 Ti enters the fray unabated by any direct competitor, and as such it’s only got to impress us enough to prove it’s worth $399 of our pay packet. And it surely does.
Specifications
(Image credit: Nvidia)
Nvidia RTX 3060 Ti specs
The RTX 3060 Ti features a cut-down GA104 GPU at its not-so-gooey silicon centre, even so delivers more than a modicum of CUDA Cores with a total of 4,864. That’s markedly above the RTX 2080 Super at 3,072 CUDA Cores and a significant departure from the RTX 2060 Super at 2,176.
Let us not forget the RTX 2060 Super is, for all intents and purposes, the RTX 3060 Ti’s opposite number for the RTX 30-series. The two cards’ price tags match at launch, at $399 (£369), but the significant pull of the RTX 3060 Ti towards the performance of the RTX 2080 Super yet again shows the tremendous generational leap being introduced with the Ampere architecture.
RTX 3060 Ti specs
GPU — GA104
Lithography — Samsung 8nm
Die size — 392mm2
Transistors — 17.4 bn
CUDA cores — 4,864
SMs — 38
RT Cores — 38
Tensor Cores — 152
GPU Boost clock — 1,665MHz
Memory bus — 256-bit
Memory capacity — 8GB GDDR6
Memory bandwidth — 448GB/s
TGP — 200W
Launch price — $399 (£369)
The RTX 3060 Ti features a decent boost clock at 1,665MHz, rendered partially irrelevant due to Nvidia’s GPU Boost technology, which will often see this GPU far exceed that under load—around 1,875MHz on average. That makes it the fastest of the RTX 30-series so far. This is also a reference Founders Edition card so we’re not looking at any overclocking out of the box. However, general availability of the Founders Edition coincides with the launch of AIB third-party RTX 3060 Ti’s (December 2, 2020), so keep an eye out for OC models if you’re interested in pushing things a little more.
You’ll miss out on the Founders Edition shroud if you do, however. It’s near-enough the exact same cooler design as the RTX 3070, which makes it on par with my personal favourite of the lot, but it does differ in one minor way: The tone of the metal finish on the RTX 3060 Ti is considerably lighter than the dark grey for the three 30-series cards above it.
That just pushes the RTX 3060 Ti to the top of the leaderboard in my eyes, but it’s purely an aesthetic shake up. Both offer near-enough the same quiet and cool operation as the rest bearing Nvidia’s own-brand heat sink and clever cut-out cooler, and it similarly makes use of the new compact 12-pin power connector. Don’t worry, there’s a single 8-pin to 12-pin adapter included in the box.
Yet these are mostly aesthetic changes, and while that cooler provides more than adequate chilling power, it’s the overhaul to the rasterised rendering pipeline across the Ampere architecture that is the architect of its performance boon.
The specifics of which you can read more about in our Nvidia RTX 3080 review , but once again for those in the back…
Each streaming multiprocessor, or SM, within Nvidia’s RTX 30-series GPUs has received double the number of floating point (FP32) units as past GPU generations. The benefit of which is greater parallelism and the ability to not only alternate between integer and floating point operations depending on the workload but utilise a greater number of FP32 units when there are fewer integer operations required. That happens a lot of the time in gaming, hence the switch.
The FP32 units within any given GPU are also what Nvidia counts as the CUDA Core total for each GPU specification. So when comparing the RTX 30-series with the RTX 20-series, the reality of such an architectural split becomes abundantly clear.
Image 1 of 3
(Image credit: Nvidia)
Image 1 of 3
(Image credit: Nvidia)Image 1 of 3
(Image credit: Nvidia)Image 1 of 3
Where you might expect a card closer to the 2,176 core count of the RTX 2060 Super, we’re now looking at the 4,854 CUDA Core RTX 3060.
The same could be said for the 4,352 CUDA Core RTX 2080 Ti’s (sort of) opposite number, the RTX 3090, fit with 10,752 CUDA Cores.
It’s all been an effective experiment in GPU topology, too, with existing RTX 30-series GPUs managing to dominate their RTX 20-series counterparts. And I’m pleased to report that the RTX 3060 Ti is no different. But we’ll get to that.
With a capacity at 8GB of GDDR6 and a complimentary 256-bit memory bus, the RTX 3060 Ti is capable of an overall memory bandwidth of 448GB/s—a match for the RTX 3070 in every way. That’s the only possible concern for any potential buyer from the specs list that I can point to with any possible consternation.
It’s not that an 8GB memory capacity has seemingly much of an impact on gaming performance right now—we’ve seen as much fairly consistently through our testing of AMD’s 16GB RX 6800-series cards and the 10GB RTX 3080 and 8GB RTX 3070. But that’s not to say it won’t at some time or another.
I won’t speak to unsubstantiated rumour too greatly within a review, but we’ve heard multiple rumours for yet unannounced RTX 30-series cards with possible higher memory capacities than those currently available, including an RTX 3080 with 20GB VRAM, an RTX 3080 Ti with 20GB VRAM, and even an RTX 3060 with up to 12GB VRAM.
It’s hardly proof of anything, I must admit. But it does make me wonder whether it’s merely a reflexive action in light of AMD’s 16GB (and possible 12GB) RX 6000-series graphics cards, or if there is some dark cloud approaching for those of us that own cards with, perhaps let’s say, modest memory capacities and overall bandwidth.
Every game developer I’ve spoken to has been keen to make better use of greater high-speed memory stores for more elaborate textures and the like, but that shouldn’t necessarily mean anyone with less than a given memory buffer will be all out of luck. Scalability is still the name of the game for almost every walk of development, and not the least bit PC gaming.
But as I say, that’s not so much a reality we’re having to deal with today. The RTX 3060 Ti manages to maintain a steady canter in modern games across 1080p, 1440p, and even 4K—which is the first time I believe we can safely say that of an xx60-level graphics card without laboured breath or serious caveats.
Performance
(Image credit: Nvidia)
Nvidia RTX 3060 Ti performance
With roughly 17% fewer CUDA Cores than an RTX 3070, you can almost have a guess where RTX 3060 Ti performance will land with with pretty comfortable accuracy.
You wouldn’t be all that far off just calling it a day at around a 17% delta between the two, either. At its worst, you’ll see almost exactly 17% between the two cards. But don’t forget there is a clock speed differential to factor in between the two that can throw things a little out of whack in a handful of games, and sometimes the RTX 3060 Ti can stick within high single-digits of the RTX 3070 frame rates.
But that’s hardly a referential touchstone we can all get behind—what with very few RTX 3070s available to purchase today. Instead, it’s the RTX 2080 Super that the RTX 3060 Ti bears down upon. For the most part, you’ll find the RTX 3060 Ti a nose ahead of the RTX 2080 Super, with the odd exception (increasingly at lower resolution) where the RTX 2080 Super just manages to inch into the lead.
Ampere’s 2nd gen RT cores show their worth across ray tracing benchmarks, too, and despite having fewer of them (RT Core count is tied to SM count) the RTX 3060 Ti is more than a match for the RTX 2080 Super in ray-traced games—which is pretty impressive for 12 fewer RT Cores.
4K gaming performance
Image 1 of 8
(Image credit: Future)
Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
With even the RTX 2070 deemed worthy of 4K performance, the fact we’re seeing the RTX 3060 Ti managing to push around more than eight million pixels, with relative ease, should come as no surprise.
The RTX 3060 Ti trades blows with the RTX 2080 Super throughout our benchmarking, but at 4K you see it tends to win out over the Turing card.
Perhaps it’s the increased FP32 unit count coming into play, as both cards feature very similar memory configurations at 8GB of GDDR6 and a 256-bit memory bus.
And there’s something to be said for the RTX 3060 Ti managing, in some games, to stay not far off the pace of the RTX 3070. With very similar configurations, that’s perhaps none too surprising, but if you consider the RTX 3060 Ti is launching at $399, 20% cheaper than the RTX 3070, and managing to stay within a single-digit frame rate delta at times, that’s a pretty good showing from the pared-down GPU.
1440p gaming performance
Image 1 of 8
(Image credit: Future)
Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
Once again, the RTX 3060 Ti is dominating Nvidia’s RTX 2080 Super at 1440p.
Usually by a pretty significant lead, too. Civilization VI appears to be a game that favours the older architecture at higher resolution—make sense of that one—and it’s all tied up in F1 2020, but this is a clear win for Ampere and the RTX 3060 Ti.
With framerates creeping upwards of 144fps in the least demanding games, and well over 60fps in those with an insatiable hunger for performant GPUs, the RTX 3060 Ti makes a great case for itself as a fantastic 1440p graphics card, and one that should see you well taken care of until 4K GPUs and monitors drop in price to become a little more affordable.
1080p gaming performance
Image 1 of 8
(Image credit: Future)
Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
The RTX 3060 Ti could be seen as a great GPU for high refresh rate gaming at 1080p.
There’s not too much wasted resource in colossal memory buffers and the like, and so you get a decent blend of performance and cost.
That’s pretty clear once again from the benchmarks, which see the RTX 3060 Ti sitting comfortably ahead of the RTX 2080 Super in all but F1 2020, which seemingly adores both Turing and the RX 6800-series cards. It’ll be interesting to see how this one shakes out with, what can only be, the inevitable RX 6700-series competition from the red team. But all in good time.
For now, the RTX 3060 Ti carves out a heap of 1080p performance, and even closes in on the RTX 3070 in a couple of games.
Ray tracing performance
Image 1 of 8
(Image credit: Future)
Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
(Image credit: Future)Image 1 of 8
The Nvidia Ampere architecture comes with second generation RT Cores, and third generation Tensor Cores, with the Volta architecture initially introducing those AI accelerators way back when.
It’s clearly a superior approach by a decent degree over the previous Turing acceleration, and obviously against the Radeon version too, and that goes a long way to explaining how the RTX 3060 Ti with just 38 RT Cores can outperform the RTX 2080 Super with 48 RT Cores.
It’s pretty close, but with a slight rasterised performance edge in the RTX games we’ve tested above, and the improvements to Ampere’s RT acceleration, the RTX 3060 Ti comes out way on top.
The RTX 3060 Ti’s ray tracing performance also goes a long way to raising the floor for overall ray tracing performance, with a significant advantage over the RTX 2060 Super with 34 (Gen 1) RT Cores.
Power and thermal
Image 1 of 3
(Image credit: Future)
Image 1 of 3
(Image credit: Future)Image 1 of 3
(Image credit: Future)Image 1 of 3
Test rig
CPU — Intel Core i7 10700K
Motherboard — MSI MPG Z490 Gaming Carbon WiFi
RAM — Corsair Vengeance RGB Pro @ 3,200MHz
CPU cooler — Corsair h200i RGB Pro XT
PSU — NZXT 850W
Chassis — DimasTech Mini V2
There’s not much about the RTX 3060 Ti that’s particularly surprising, and the fact it’s the most power efficient GPU of the RTX 30-series so far doesn’t really change thing.
With a 200W TDP, the RTX 3060 Ti occasionally sucks upwards of 232W from the PSU, but mostly maintains a steady gait at 200W or a little less.
That puts it ahead of the RTX 3070 by just a touch in performance per watt at 1080p, and in line with the rest of Ampere at 4K. That’s notably off the performance per watt of AMD’s RX 6800 and RDNA 2, which could give AMD a little more leeway when it comes to eventual RX 6700-series SKUs, should they show up anytime soon.
Verdict
(Image credit: Nvidia)
Nvidia RTX 3060 Ti verdict
Once again we’re looking at a solid generational leap from Nvidia’s Ampere generation, and the RTX 3060 Ti delivers superb performance across a heady mix of rasterised and ray-traced games. If you’re looking for a steady 60fps or more in the latest, most demanding games, then it’s got you covered. If you want a little more more out of 1080p, you’re sorted well into high refresh rate territory.
And if you hope for 60fps at 4K, that’s attainable with only marginal sacrifices to graphics settings.
Just what you might expect from an RTX 3060 Ti, no doubt.
Nvidia has also made significant gains in its mission to quash any and all frame rate sacrifice associated with true-to-life reflections and dynamic global lighting. There’s undoubtedly still a performance hit from switching ray tracing on, but Nvidia’s new and improved RT Cores, along with DLSS in many cases, takes some of the oomph out of the swing.
And that’s an important thing to note as we head into PC gaming’s third year of ray tracing (yes, it’s been that long!). There’s already a far more expansive library of ray tracing compatible titles than when Nvidia first launched the RTX suite back in 2018, and it’s sure to only grow with AMD, and AMD-powered consoles from Sony and Microsoft, now supporting ray tracing acceleration on-chip.
Your next upgrade
(Image credit: Future)
Best CPU for gaming : the top chips from Intel and AMD
Best graphics card : your perfect pixel-pusher awaits
Best SSD for gaming : get into the game ahead of the rest
The same can be said for DLSS.
The feature is become slightly more widespread in today’s most played games, and it’s becoming an especially useful tool for not only acting as counterweight to the ray tracing performance impact, but actually as a tool for reducing render load at high resolutions—a lot of the time on GPUs that materially don’t have the guts to make it work.
The RTX 3060 Ti is such a card. While it dabbles in high-fidelity 4K gaming, some graphics settings need to be reduced in order to really crack a solid 60fps in more demanding games. And that’s often just in terms of average framerates, to keep your GPU steadily above 60fps may require quite a bit of tinkering. That can sometimes take the fun out of 4K gaming in the first place, the supposed high level of detail.
So while DLSS is far from a universal solution, it’s a surprisingly not all that lossy way to hit those all-important performance figures for smooth gaming. DLSS has come on leaps and bounds since its first introduction, and in most games it’s not something that detracts from the visual or gaming experience in any tangible way.
And it’s these extra features—ray tracing, DLSS, Reflex, and even Nvidia Broadcast—that generate quite a bit of my interest in the RTX 3060 Ti today beyond its rasterised performance. There’s a solid base of genuinely great features behind RTX and the Nvidia package that’s only been improved upon with Ampere, none more so than the ray tracing performance for that matter.
That’s not to say AMD doesn’t offer its fair share of alternatives in FidelityFX and Radeon Anti-Lag. But we’re yet to see an AMD alternative to the supersampling feature, although one is confirmed to be on the way at some point next year in FidelityFX Super Resolution. And, while ray tracing is no longer an Nvidia-only experience with the introduction of the RX 6800-series, it is an area where the green team is dominating performance graphs.
The RTX 3060 Ti delivers superb performance across a heady mix of rasterised and ray-traced games
The same goes for a direct competitor to the RTX 3060 Ti—we don’t know when it will arrive, but you can be sure that one will.
Likely under the RX 6700-series banner.
And that’s a common footing we find ourselves in with Nvidia’s launches so far this generation—the company has materialised graphics cards ahead of AMD’s comparative lineup, and that means that we won’t truly know if AMD’s got a trick up its sleeve to compete with the RTX 3060 Ti until likely early next year.
But that doesn’t change a thing in my mind right now. It’s not all Nvidia vs. AMD, you know, and frankly whether there’s an answer to the RTX 3060 Ti in a few months or not, you shouldn’t have any regrets in choosing this graphics card for your next big PC rebuild.
The RTX 3060 Ti delivers gaming performance that’s rather stupendous when you look at generational gains over even the RTX 20-series—next to the 10-series it’s quite frightening, actually. There’s exceptional 1080p and 1440p performance in a tiny package here, the likes of which would’ve set you back something close to twice as much cash only last year. And that’s pretty great.
There’s just the small potential issue of availability, that which has similarly loomed over all the other RTX 30-series launches to date. I’m happy to be proven wrong, but judging by every tech launch this year (not only Nvidia’s, and not only graphics cards), stock may be sparsely found for the RTX 3060 Ti at launch due to immense demand for new silicon right now.
Global availability for the RTX 3060 Ti begins December 2, 2020, and I suspect you’ll want to be ready to go, front and centre, if you want to have any hope of picking up this graphics card on launch day, or likely anytime before 2021. And given the price and performance of this mid-range Ampere card, it will be worth getting in line for.
Read our review policy
Nvidia RTX 3060 Ti review Founders Edition
The RTX 3060 Ti is exactly what we expected from a fourth-tier RTX 30-series graphics card, but that’s no mark against it. Nvidia’s Ampere cards offers an almost unprecedented leap in gaming performance over past generations, and the RTX 3060 Ti manages to deliver more of the same on a slimmer budget.
Jacob earned his first byline writing for his own tech blog from his hometown in Wales in 2017. From there, he graduated to professionally breaking things as hardware writer at PCGamesN, where he would later win command of the kit cupboard as hardware editor. Nowadays, as senior hardware editor at PC Gamer, he spends his days reporting on the latest developments in the technology and gaming industry. When he’s not writing about GPUs and CPUs, however, you’ll find him trying to get as far away from the modern world as possible by wild camping.
PC Gamer is part of Future plc, an international media group and leading digital publisher. Visit our corporate site .
©
Future Publishing Limited Quay House, The Ambury,
Bath
BA1 1UA. All rights reserved. England and Wales company registration number 2008885.
Nvidia GeForce RTX 3050 review: effectively the RTX 1660 Ti
Skip to main content
PC Gamer is supported by its audience. When you purchase through links on our site, we may earn an affiliate commission.
Here’s why you can trust us.
Gigabyte’s RTX 3050 Eagle shows us Nvidia’s mainstream GPU has GTX 1660 Ti power with RTX sensibilities.
(Image: © Future)
Our Verdict
We’re essentially looking at Nvidia taking away the ‘GTX’ prefix and giving us an RTX 1660 Ti. That makes it a good 1080p GPU, though the addition of DLSS support is far more tempting a proposition, especially at this level of GPU, than the promise of 1080p ray traced gaming. Fingers crossed it stays in stock at a reasonable price.
For
- DLSS and ray tracing support
- Way faster than an RX 6500 XT
Against
- Should be at least RTX 2060 performance
- Long term stock and pricing unknowable
Graphics cards are a real pain point for PC gaming. Hell of an opening sentence to a new GPU review, I know, but that is the world we inhabit in 2022. Supply is constrained and demand is as sky-high as the prices of said GPUs.
So, it was with a faint taste of something akin to hope on my lips I approached the launch of new mainstream graphics cards from both AMD and Nvidia.
If you’ve peeped the lowest score I think I’ve given anything in my time since coming back to PC Gamer then you’ll know how the AMD Radeon RX 6500 XT turned out. Now it’s Nvidia’s turn to either save the day or disappoint us all with the GeForce RTX 3050. I mean, there can’t be any middle ground, can there? Somewhat inevitably, that’s going to depend very much on your point of view.
Still, I’m feeling a little better about the budget-conscious end of the PC gaming market since enjoying the fruits of Intel’s Core i5 12400 labours, and its seemingly accidental overclocking bounty. A $200 chip that can comfortably nail 5.2GHz, with an affordable motherboard platform to boot? Well, that has the potential to be the perfect base for your next gaming rig. All we need is an affordable GPU to go with it.
This is where Nvidia steps in with the nominally $250 RTX 3050, promising to blow the RX 6500 XT out of the water for just $50 more.
As it turns out MSRPs evaporate as soon as the first wave of GPUs sell out—generally in the first ten minutes—so we have the $280 Gigabyte RTX 3050 Eagle here, which is actually marginally cheaper than the $300 Gigabyte RX 6500 XT we reviewed as our first taste of AMD’s budget GPU.
And it does indeed blow the RX 6500 XT out of the water. But we are still essentially talking about a new Nvidia graphics card with GTX 1660 Ti gaming performance, though one with the added veneer of ray tracing hardware and DLSS support.
Nvidia RTX 3050 specs
(Image credit: Future)
What are the RTX 3050 specs?
The comparisons both AMD and Nvidia have made with their new cards generally hides where they actually sit in terms of relative performance. Both have spent an irrelevant amount of time putting their new cards up against the GTX 1650, with AMD also pitting the RX 6500 XT against the RX 570, and Nvidia the RTX 3050 against the GTX 1050 .
None of these comparisons make sense.
The AMD card’s poor performance is more ably highlighted by a comparison with the RX 5500 XT and RX 480—similarly specced and priced cards from generations back—and it is more meaningful to compare the RTX 3050 with the $279 GTX 1660 Ti than the $149 GTX 1650 or GTX 1050.
| RTX 3050 | RTX 2060 | GTX 1660 Ti | |
|---|---|---|---|
| GPU | GA106 | TU106 | TU116 |
| Transistors | 12 billion | 10.8 billion | 6.6 billion |
| Die size | 276mm2 | 445mm2 | 284mm2 |
| Streaming multiprocessors (SMs) | 20 | 30 | 24 |
| CUDA cores | 2560 | 1920 | 1526 |
| Tensor Cores | 80 | 240 | NA |
| RT Cores | 20 | 30 | NA |
| ROPs | 48 | 48 | 48 |
| Base clock speed | 1,552MHz | 1,365MHz | 1,500MHz |
| Boost clock speed | 1,777MHz | 1,680MHz | 1,770MHz |
| Memory | 8GB GDDR6 | 6GB GDDR6 | 6GB GDDR6 |
| Memory bus | 128-bit | 192-bit | 192-bit |
| Memory bandwidth | 224GB/s | 336GB/s | 288GB/s |
| TGP | 130W | 160W | 120W |
| Reference price | $249 | $349 (then $299) | $279 |
The GA106 GPU Nvidia reportedly has at the heart of the RTX 3050 is a smaller version than that used in the RTX 3060 which makes it roughly the same size as the chip used in the old GTX 1660 Ti.
It does though have almost double the number of transistors at its heart and, thanks to the excellent Ampere architecture it comes with over one thousand more shaders inside it.
It is also notable that AMD’s latest GPU, the Navi 24 silicon inside the RX 6500 XT is a 107mm2 chip, while the GA106 is something in the region of 276mm2. That’s something which will likely come into play when it comes to manufacturing and the numbers of GPUs that each company can produce to fulfil the demand for their cards.
Those 2,560 CUDA cores in the RTX 3050 are split between 20 SMs which also then delivers 20 RT cores and 80 Tensor cores. It’s those last two specs that separate the RTX 3050 from its GTX 1660 Ti brethren and ought to make it a far more tempting choice for the mainstream gamer. The RT cores are what allow for ray tracing and the Tensor Cores then allow you to enable DLSS to make ray tracing actually playable at a decent frame rate, all thanks to the magic of AI-powered super sampling.
The RTX 3050 has a similar total graphics power (TGP) compared with the GTX 1660 Ti, too, with 130W vs. 120W for the older card. Along with that extra 10W, you also get another 2GB of GDDR6 memory for a total of 8GB. Though that runs on a thinner 128-bit aggregated memory bus compared with the GTX 1660 Ti’s 192-bit bus, which is why you end up with less memory bandwidth as a result.
Nvidia RTX 3050 performance
(Image credit: Future)
How does the RTX 3050 perform?
Our standard game benchmarks are always carried out without any form of resolution output modifiers to get an idea of the raw performance of any new GPU. As such we don’t traditionally test with DLSS or FidelityFX Super Resolution enabled. Though, as more and more games are shipping with the technology, and a wider breadth of hardware supports it, it always has to be a consideration when we talk about the overall package of a new release.
So, while the benchmarks highlight where the RTX 3050 is more or less akin to the GTX 1660 Ti in terms of its straight gaming performance, there is the promise of DLSS working those Tensor Cores to actually make the card a pretty capable 1440p gaming GPU where the technology is enabled.
The same was true of the RX 6500 XT, with FidelityFX Super Resolution, too. But its severely restricted frame buffer means game performance is still pretty weak even with FSR enabled. It’s also not as effective a solution as Nvidia’s hardware-based DLSS tech.
1080p gaming performance
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
1440p gaming performance
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
Image 1 of 8
New vs. Old
Image 1 of 7
Image 1 of 7
Image 1 of 7
Image 1 of 7
Image 1 of 7
Image 1 of 7
Image 1 of 7
Image 1 of 7
Upscaling performance
Image 1 of 2
(Image credit: Future)
Image 1 of 2
(Image credit: Future)Image 1 of 2
System performance
Image 1 of 3
Image 1 of 3
Image 1 of 3
Image 1 of 3
Nvidia RTX 3050 analysis
(Image credit: Future)
How does the RTX 3050 stack up?
The GeForce RTX 3050 is a funny one.
You could say Nvidia has pulled a similar move to AMD in creating a new graphics card with the same performance as that of a previous generation for effectively the same amount of money. We rightly castigated AMD for essentially giving us a worse version of the RX 480 nearly six years later, but you could say Nvidia has done only marginally better by just stepping one generation back to slightly better than GTX 1660 Ti performance.
Though that is a little unfair because the Ampere architecture at the heart of the RTX 3050 is fundamentally better than that of the Turing GPU at the heart of the GTX 1660 Ti. Again, the same can be said of the RDNA 2 tech beating beneath the RX 6500 XT’s oversized coolers, when compared to the Graphics Core Next (GCN) of the RX 480.
This is where AMD’s preference for openness and an aversion for fixed-function hardware does kind of backfire. While FSR is supported on a range of older AMD graphics cards, DLSS is restricted to those with the RTX prefix and the necessary GPU hardware.
And that gives the RTX 3050 a definite edge over its Turing forebears and means that, while it is essentially the same price and very close in performance, the extra feature set makes it just about a worthy successor.
By a 2022 reckoning anyways. Which is always skewed away from the previous norms of the GPU world. Though if you’re currently running a GTX 1660 Ti, I’d still say it’s probably not worth the upgrade.
I am a huge fan of DLSS, however, and it does mean that the RTX 3050 isn’t just a good 1080p gaming GPU, it’s actually capable of running happily on a 1440p display too. Though DLSS isn’t in every game and Nvidia’s new game-agnostic Nvidia Image Scaling (roughly analogous to FSR) is available to its older GPUs, too.
But you do also get a little 1080p ray tracing support with the new RTX 3050. Again, that’s thanks to DLSS now offering support for 1080p as a native resolution and rendering below that native res. There’s less detail available, so it’s tougher to get a great image, but DLSS still does an impressive job at allowing games such as Control and Wolfenstein Youngblood to offer playable ray tracing on a sub-$300 GPU.
The tough thing is our traditional expectations, though. We always want more from successive generations, and that means we want more performance, not just access to more features from our GPUs. At a minimum, I would have wanted RTX 2060 levels of raw gaming performance, especially as that was a $299 card at the start of 2020 and we’re looking at $280 cards right here with the RTX 3050.
Then there’s the thorny issue of stock, and how much Nvidia is able to get to its partners to make graphics cards and for them to get them into the channel for us to buy. We’ve been told that there is healthy stock available at launch and that there will definitely be reference-priced units there, too. But we’re always told that, and stock always vanishes.
It will this time, too, and the $250 reference-price units will last as long as the initial stock does, then I would bet we never see another MSRP card available again. That’s part of the problem with Nvidia not creating reference-priced Founders Edition cards at this level of the GPU stack—there’s no competition for manufacturers wanting to pump out higher-priced options, and so that’s all we’ll see in retail after tomorrow’s launch.
Where I wanted at least RTX 2060 performance, I’ve got GTX 1660 Ti frame rates with a little RTX frosting on top
The hope is that, like the RX 6500 XT, there will continue to be RTX 3050 cards available weeks after launch and, even if they’re not at MSRP, aren’t topping the $300 mark. Please.
Whether that happens remains to be seen. AMD has cut the RX 6500 XT GPU to shreds, so it’s less than half the size of the GA106 GPU in the RTX 3050, which means it can theoretically manufacture far more in the same amount of time because it gets more chips out of the same size silicon wafer. Maybe that’s why there are more Radeon cards available a week on from launch , maybe AMD’s gamble has paid off.
We’ve got to hope that Nvidia is still able to keep the chips flowing from Samsung’s 8nm fabs so the RTX 3050 remains in stock at a reasonable price. Because, while it’s maybe not the stellar budget GPU we were hoping for, it’s still an effective sub-$300 graphics card capable of utilising the best GPU tech of a generation and delivering a gaming upgrade for those on lower-spec silicon than a GTX 1660 Ti.
Nvidia RTX 3050 verdict
(Image credit: Future)
Should you buy an RTX 3050?
AMD and Nvidia have taken different approaches to the conundrum of creating a high-volume budget GPU in a chip shortage. AMD slashed the size of its silicon, betting on high clock speeds to give it just enough performance to offer some mainstream 1080p gaming chops, while its teeny tiny GPU meant it could manufacture more GPUs than the competition and effectively become the only option at this price.
Nvidia has gone for a more performance-first tactic. Where the RTX 3050 and RX 6500 XT are effectively sitting in the same price bracket, you’d absolutely rather have the Nvidia card for the money. At worst it’s 20% faster than the Radeon GPU, and can actually deliver 1440p gaming in places where the 4GB frame buffer of the RX 6500 XT won’t allow it to tread foot. Throw the magic of DLSS into the mix—still a more effective solution than FSR—and the RTX 3050 looks like a certain winner in this head-to-head.
But, where I wanted at least RTX 2060 performance, I’ve got GTX 1660 Ti frame rates with a little RTX frosting on top. Sure, that’s tasty where it sticks, but is another example of a card designed and priced within the limits of a pandemic and a GPU shortage, rather than showing off Nvidia’s silicon wizardry to its fullest.
TODAY’S BEST DEALS
Read our review policy
GeForce RTX 3050
We’re essentially looking at Nvidia taking away the ‘GTX’ prefix and giving us an RTX 1660 Ti. That makes it a good 1080p GPU, though the addition of DLSS support is far more tempting a proposition, especially at this level of GPU, than the promise of 1080p ray traced gaming. Fingers crossed it stays in stock at a reasonable price.
Dave has been gaming since the days of Zaxxon and Lady Bug on the Colecovision, and code books for the Commodore Vic 20 (Death Race 2000!). He built his first gaming PC at the tender age of 16, and finally finished bug-fixing the Cyrix-based system around a year later.
When he dropped it out of the window. He first started writing for Official PlayStation Magazine and Xbox World many decades ago, then moved onto PC Format full-time, then PC Gamer, TechRadar, and T3 among others. Now he’s back, writing about the nightmarish graphics card market, CPUs with more cores than sense, gaming laptops hotter than the sun, and SSDs more capacious than a Cybertruck.
PC Gamer is part of Future plc, an international media group and leading digital publisher. Visit our corporate site .
©
Future Publishing Limited Quay House, The Ambury,
Bath
BA1 1UA. All rights reserved. England and Wales company registration number 2008885.
2022 PC gaming graphics cards
NVIDIA or AMD, GTX or RTX? Buy now or wait for the next generation? Questions like these haunt you when it’s time for an upgrade. To help you solve at least some of them, we have compiled a list of the best graphics cards at the moment.
NVIDIA
NVIDIA GeForce RTX 3090 Ti
GPU — GA102 | CUDA Cores – 10,752 | Memory — 24GB GDDR6X | Bus — 384-bit
Pros :
- Ultimate Power
- Large memory
- Ideal for 4K resolution
Cons :
- Out of reach for most gamers
- Uses a lot of energy
The
GeForce RTX 3090 Ti was designed for enthusiasts who don’t accept compromise and are willing to pay for the pleasure of owning the world’s most powerful graphics card.
Indeed, it has an advanced graphics processor, and the list of supported technologies takes up a whole page. The graphics card will easily handle any modern games at 4K resolution with ray tracing enabled (especially if you use the DLSS function). Among the shortcomings of the video card — prohibitively high price, indefatigable power consumption and large dimensions.
NVIDIA GeForce RTX 3090
GPU — GA102 | CUDA cores — 10,496 | Memory — 24GB GDDR6X | Bus — 384-bit
Pros :
- Very powerful
- Large memory
- Good for both gaming and professional use
Cons :
- Very expensive
The Nvidia GeForce RTX 3090 costs $500 less than the GeForce RTX 3090 Ti, while not losing much power to the older model. It’s a great graphics card for 4K and 1440p gaming as well as professional tasks like video editing and 3D modeling.
However, it is still very expensive, especially considering that it is not easy to find a video card at the suggested retail price. The adapter consumes 100 watts less power than the 3090 Ti, which will significantly offload your power supply. And take care of the presence of a spacious case that can accommodate an overall three-slot video card.
NVIDIA GeForce RTX 3080 Ti
GPU — GA102 | CUDA Cores – 10,240 | Memory – 12GB GDDR6X | Bus — 384-bit
Pros :
- Support for modern rendering and visualization technologies
Cons :
- Back-to-back memory for 4K games
- 12-pin power connector included
The
3080 Ti is designed with gamers in mind, so it supports all the latest technologies for an unrivaled gaming and streaming experience. Among them are DLSS, and ray tracing, and Nvidia Reflex, and an encoder for better image transmission through streaming, and Resizable BAR, and much more.
The graphics card is powerful enough to run games at maximum settings in 4K resolution and with DLSS: it provides more than 60 fps in all modern AAA titles. You can count on this graphics adapter to provide you with high performance for years to come.
NVIDIA GeForce RTX 3080
GPU — GA102 | CUDA Cores – 8,960 | Memory — 10/12GB GDDR6X | Bus — 320/384-bit
Pros :
- More powerful than RTX 2080 Ti
- Supports modern technologies
- Good for 1440p and 4K
Cons :
- Not enough memory to play in high resolution
- 12-pin power connector
The GeForce RTX 3080 outperforms the RTX 2080 Ti by approximately 15%, while the new graphics card packs more features than the previous generation.
You can still play 4K with this video card and there is no game that it can’t handle at 1440p, but with ray tracing enabled, you’ll have to make compromises in the form of lower settings.
And using the newfangled 12-pin power connector will force you to look for an appropriate adapter or upgrade the power supply.
NVIDIA GeForce RTX 3070 Ti
GPU — GA104 | CUDA Cores – 6,144 | Memory – 8GB GDDR6X | Bus — 256-bit
Pros
Nvidia developed the GeForce RTX 3070 Ti as a «response» to its closest competitor, the AMD RX 6800. The answer was controversial: the model outperforms its rival in 4K resolution, but is slightly inferior in 1440p and 1080p. However, with the activation of ray tracing and DLSS, Nvidia’s adapter wins a clear victory.
This is a good graphics card if you don’t plan on playing at 4K resolution, where it’s getting too small, and by that we mean making trade-offs in the form of lower settings or frame rates. On the other hand, we would recommend paying a little extra and getting an RTX 3080.
NVIDIA GeForce RTX 3070
GPU — GA104 | CUDA Cores – 5,888 | Memory – 8GB GDDR6 | Bus — 256-bit
Pros
Cons :
- 12-pin connector
- Weak for 4K
The
RTX 3070 is great if you’re not going for max settings and high resolutions.
With this graphics card, you can comfortably play at 1440p, and it supports all modern Nvidia technologies, including RTX, DLSS, Resizable BAR and so on. In terms of performance, it compares with the RTX 2080 Ti, the flagship of the previous generation, which is a very good result for a middle-class video card.
At the same time, this model is smaller than the older representatives of its generation, less noisy and more energy efficient. The disadvantages include the presence of a 12-pin power connector, although this should not be a big problem, given that the manufacturer puts in the kit an adapter for power supplies that are not equipped with the appropriate connectors.
NVIDIA GeForce RTX 2080 TI
GPU — TU102 | CUDA Cores – 4,352 | Memory — 11GB GDDR6 | Bus — 352-bit
Pros :
- Serious Gaming — 4K/60fps
- Faster than $3,000 Titan V
- All the goodies of ray tracing and AI
Cons :
- Conservative price tag
Here it is, the true nextgen.
GPU based on the Turing architecture, ultra-modern and unsurpassed «king of graphics». While the RTX 2080 and 2070 Super are able to match the performance of the GTX 1080 Ti, this card leaves them far behind, giving you 4K/60fps in all but the most demanding games today.
No matter how you feel about newfangled (for PC gaming) ray tracing technology, there’s no getting away from it in the future, and the RTX 2080 Ti is ready for it. With the release of PS5 and Xbox Series X consoles that support ray tracing, there are more and more games with appropriate graphic effects, and sooner or later you will have to upgrade.
NVIDIA GeForce RTX 3060 Ti
GPU — GA104 | CUDA Cores – 4,864 | Memory – 8GB GDDR6 | Bus — 256-bit
Pros :
- Ideal for playing at 1440p and 1080p
- Quiet
- Energy efficient
- Relatively affordable
GeForce RTX 3060 Ti could become a new «people’s» video card, if not for the shortage and high prices for devices in this segment of computer technology.
However, owners of the model can count on excellent performance at 1440p and 1080p, and for 1080p you don’t even need to use DLSS when ray tracing is activated — the video card can handle it.
Unlike the «monsters» of energy consumption in the face of older models, 3060 Ti is energy efficient and quiet. In terms of performance, it can be compared with the more expensive RTX 2080 SUPER, and we would recommend buying this video card to those who have finally decided to switch from a Pascal family video card to something new.
NVIDIA GeForce RTX 2080 SUPER
GPU — TU104 | CUDA Cores – 2,944 | Memory – 8GB GDDR6 | Bus — 256-bit
Pros :
- Excellent 4K gaming
- RTX Turing architecture
Cons
The days of the RTX 2080 were numbered as soon as Nvidia admitted to releasing a Super version soon. The new graphics card outperforms the GTX 1080 Ti with more cores and faster memory. And yet, the latter has the best performance with tracing the best at the turn of up to $1000. GPU — TU104 | CUDA Cores – 2,560 | Memory – 8GB GDDR6 | Bus — 256-bit Pros : Cons : The RTX 2070 Super was born to win with the new Navi chips. As AMD took aim at the old RTX 2070, Nvidia released an upgraded version that is cheaper and slightly inferior to the 2080. It’s fast. Really fast. Impressive 4K can be squeezed out of this card, far ahead of Pascal’s best result on the GTX 1080 Ti. GPU — GA106 | CUDA Cores – 3,584 | Memory — 12GB GDDR6 | Bus — 192-bit Pros : Cons : The GeForce RTX 3060 boasts a low suggested retail price, as well as good performance at 1080p and 1440p, combined with a whopping 12 GB of video memory. The latter, however, is debatable, since this amount is redundant for playing at resolutions lower than 4K. Although, on the other hand, there is never enough memory. The graphics card allows you to play with ray tracing, provided you’re willing to compromise and don’t mind turning on DLSS — without intelligent anti-aliasing, the RTX 3060 can’t do much with RT enabled. GPU — TU106 | CUDA Cores – 2.176 | Memory – 8GB GDDR6 | Tire — 256-bit Pros : Cons : The RTX 2060 is the bare minimum required to enter the magical world of ray tracing (even though the technology isn’t perfect yet, RTX games are truly transforming). More importantly, thanks to DLSS 2.0, you can play games at 1440p resolution with no fps loss and with maximum graphics settings with this video card. If you choose between RTX 2060 and RTX 2060 SUPER, then we would recommend the second one: it has better overclocking potential, more memory and higher frequency, which means it will stay relevant longer compared to the younger version. GPU — GA106 | CUDA Cores – 2,560 | Memory – 8GB GDDR6 | Bus — 128-bit Pros : Cons : GeForce RTX 3050 is a budget option for a gaming system. This model is distinguished from similar performance video cards of the middle segment from the previous generation by supporting a larger number of current technologies. Cool and quiet, the graphics card is able to deliver acceptable frame rates at 1080p. However, it is too weak for ray tracing games, although the available tensor cores do not feel superfluous — they can be used to activate DLSS and the subsequent increase in fps. GPU — TU116 | CUDA Cores – 1,536 | Memory — 6GB GDDR6 | Bus — 192-bit Pros : Nvidia’s consumer graphics card takes advantage of the shader benefits of the Turing 20xx series architecture, but lacks the ray tracing and intelligent processing that sets the RTX line apart from other GPUs. Overclocked cards like the STRIX GTX 1660 Ti are too expensive, closer to the RTX 2060 and RX 5700, but the GTX 1660 Ti has no rivals in RRP. GPU — TU116 | CUDA Cores – 1.408 | Memory – 6GB GDDR5 | tire — 192-bit Pros : Cons : Since the introduction of Polaris GPUs in the sub-$300 segment, the GTX 1660 has taken a turn for the worse. The Nvidia card still has a slight performance advantage, which gives it the lead, offsetting the cost difference. When we spend money, we expect to get the highest possible frame rate for them, and green GPUs still meet our needs. In addition, they are equipped with new technologies Integer Scaling (scaling without blurring) and Low Latency Mode (low latency mode), which AMD graphics cards lack. GPU — TU116 | CUDA Cores – 1,280 | Memory — 4GB GDDR6 | Bus — 128-bit Pros Cons
GeForce GTX 1650 Super is enough for games at 1080p or lower. If you’re willing to lower your graphics settings, you’ll be able to get high fps, and the Turing architecture’s support for DLSS technology will further improve performance. At the same time, 4 GB of video memory is frankly not enough for modern AAA games. This will have to be taken into account if you want to download a pack of high-quality textures for your favorite title. GPU — GP107 | CUDA Cores — 768 | Memory – 4GB GDDR5 | Bus — 128-bit Pros : Cons
If the RTX 2060 is the bare minimum for ray-traced gaming, then the GTX 1050 Ti is the bare minimum for gaming. Of course, you will have to make compromises with it: it is suitable for gaming at a resolution not higher than 1080p, and it is better to forget about the maximum graphics settings. On the other hand, it is very cheap (although it could be even cheaper) and will run all modern video games — even those from the AAA segment. However, it should be noted that with the release of a new generation of consoles, its performance will no longer be enough. GPU — Navi 21 | RDNA Cores – 5,120 | Memory — 16GB GDDR6 | Bus — 256-bit Pros0025 Cons : The AMD Radeon RX 6900 XT is a direct competitor to the Nvidia GeForce RTX 3080 Ti, only losing slightly in power. With this graphics adapter, AMD is returning to the top graphics card segment for the first time since the release of the R9 Fury X. In terms of pure performance, this model breathes down the back of the Nvidia GeForce RTX 3090, but in real-world performance, things are a little more complicated, since Nvidia has an trump card in in the form of DLSS technology. On the other hand, the «red» video card is cheaper than the «green» competitors, which can be a weighty argument in its favor. GPU — Navi 21 | RDNA cores – 4,608 | Memory — 16GB GDDR6 | Bus — 256-bit Pros : Cons : The AMD Radeon RX 6800 XT takes on the Nvidia GeForce RTX 3080 by being roughly on par with the competition but with more memory, which is great for 4K and 1440p gaming. All this is true on one condition: you are ready to abandon ray tracing in games. Alas, in terms of RT support, AMD video cards lose to Nvidia solutions, so when you enable the appropriate effects, you will encounter a strong drop in frame rate. It is worth considering this nuance. GPU — Navi 22 | RDNA cores – 2,560 | Memory — 12GB GDDR6 | Bus — 192-bit Pros : Cons : AMD promises that the Radeon RX 6700 XT is able to outperform not only the GeForce RTX 3060 Ti, but even the RTX 3070, at a more modest price tag than its competitors from Nvidia. This is a great choice for 1440p games. The video card is compact, quiet and «cold». It has 12 GB of video memory, which allows you to use high-resolution textures, and reasonable power consumption. However, in terms of performance per dollar, this is not the most economical solution, so we recommend carefully weighing the pros and cons. GPU — Navi 23 | RDNA Cores – 2,048 | Memory – 8GB GDDR6 | Bus — 128-bit Pros Cons : The AMD Radeon RX 6600 XT is a smart alternative to GPUs like the Nvidia GeForce RTX 3060/Ti that delivers good gaming performance at 1080p. Traditionally for AMD video cards, this model does not cope well with ray-traced games due to the fact that competitors have DLSS support. AMD has an answer for this in the form of FSR (FidelityFX Super Resolution), but this technology is not as well established as DLSS, and is supported by fewer games. GPU — Navi 10 | RDNA cores – 2,560 | Memory – 8GB GDDR6 | Bus — 256-bit Pros : Cons : With aggressive pricing, AMD has turned out to be a real monster that can not only make the RTX 2070 Super tense, but also save money at the same time. The best part about this is that for the money, the RT 5700 XT almost takes us to the promised land of high-end GPUs, challenging the «green» gang. Still, it (in its reference form) would not be so noisy and burning. GPU — Navi 24 | RDNA Cores — 1.024 | Memory — 4GB GDDR6 | Bus — 64-bit Pros : Cons : The main disadvantage of the AMD Radeon RX 6500 XT is its small amount of memory: with 4 GB, you can forget about decent gaming performance at resolutions above 1080p. Of course, one should not even dream of ray tracing in this case. Add to this the 64-bit bus, which also affects the efficiency of the video card, and you have an option that should be settled only as a last resort. AMD, however, takes an affordable price tag and the lack of alternatives in the budget segment. For the most part, this is a plug card, but for lack of a better one, it will do. GPU — Navi 10 | RDNA Cores – 2,304 | Memory – 8GB GDDR6 | Bus — 256-bit Pros : Cons : The RX 5700, which runs on the same chip, but with cut frequencies, immediately follows its XT companion. By the way, this also affects overclocking: even in capable hands, it will still be inferior to its older sister. And it’s sad, because the RX 5700 is a great powerful graphics card with a moderate price and performance that can put Nvidia to shame in its price segment. GPU — Navi 10 XLE | RDNA Cores – 2,304 | Memory — 6GB GDDR6 | Bus — 256-bit Pros : The AMD Radeon RX 5600 XT performs well at 1080p and slightly worse at 1440p, but at 4K resolution it will show modest results. that it would be nice to add a little and get a more powerful RX 5700 XT. GPU — Navi 14 | RDNA cores — 1.408 | Memory – 4/8GB GDDR6 | Bus — 128-bit Pros : Cons : For 1080p gaming, the AMD Radeon RX 5500 XT is a good choice. But only if you choose a model with 8 GB of video memory: alas, the 4 GB version does not perform in the best way even at this resolution. The video card will be a good alternative to the outdated Radeon RX 580 and competes on equal terms with the Nvidia GeForce GTX 1650 Super, getting close even to the GTX 1660. GPU — Polaris 30 | GCN Cores — 2.304 | Memory – 8GB GDDR5 | Bus — 256-bit Pros : Cons : The latest generation of Polaris has given us 12nm chips with impressive gaming power at a very modest price tag. They are slightly inferior to the GTX Turing graphics cards, but still able to surprise. True, sometimes they can get hot… The latter has long been a problem for «red» GPUs, but you can easily find a card with additional cooling that will solve this misunderstanding. GPU — Polaris 20 | GCN Cores — 2. Pros : The price of the RX 580 has gone down, and it has found itself in the budget segment. Its price tag may not be attractive enough for many, but the video card justifies every ruble invested in it. After all, it was AMD’s flagship just a couple of years ago. Actually, it is still capable of producing impressive results in 1080p and even 1440p. GPU — Polaris 20 | GCN Cores – 2,048 | Memory – 4GB GDDR5 | Bus — 256-bit Pros : Cons : An excellent budget graphics card that can make the GTX 1050 Ti shine with its presence. Still, the 4GB RX 570 can handle the highest settings at 1080p. A real budget hero. There are a number of criteria to consider when choosing a graphics card for your gaming PC. First of all — the price: in the current realities, the cost of a graphics adapter often has the greatest impact on decision making. When choosing between Nvidia and AMD, it’s worth considering that the «green» graphics cards offer flagship performance with ray tracing and DLSS intelligent anti-aliasing technology. AMD, in turn, is betting on a more attractive price, and its cards work better with AMD processors. Intel has already joined the race between video chip manufacturers, so the choice will expand soon. Based on your monitor resolution and desired graphics settings. When it comes to video memory, the “more is better” statement is true, especially when it comes to 4K gaming. Although there are nuances here too: a weak video chip combined with a large amount of memory will not give out impressive performance. In other words, you need a balance: do not be too lazy to study the characteristics and tests of the video card so as not to mistakenly buy an “office plug” with a large amount of memory that it does not need. Any graphics card consumes power, so it’s important to make sure your power supply matches the graphics adapter’s appetites. Usually, the specifications of the video card indicate the recommended power supply, and if it is weaker than required, it is better to take care of a replacement. Top
04/21/2022 Author: Dmitry Mukharev 1 Star2 Stars3 Stars4 Stars5 Stars Big Rating of the Best Graphics Cards: for Gaming, Work and Mining 3 5 1 19 Our large rating of video cards will help you evaluate the market as a whole and choose the model that suits you. Choosing the right video card has never been an easy task, and at current prices, any mistake in this can cost you a tidy sum. Sometimes, it can be very difficult to take all this into account, and certain recommendations may not come in handy. For such cases, it is important to evaluate the market as a whole, which is why we decided to release a large rating of video cards, which will allow you to see their potential and compare them with competitors. Below is a rating of video cards based on their performance. When compiling it, we did not take into account their energy consumption, cost or price-performance ratio. This rating can be used as a guide if you really need the fastest video card, and its other parameters do not matter much to you. Fiji Let’s make a reservation right away that this is a conditional rating that can only give an approximate «picture of the world». Therefore, we advise you to use our rating only to get a rough idea of the potential of a particular video card. Computers Top 5 best video cards for mining in 2021 The Nvidia GeForce RTX 3090 Ti reigns supreme in all synthetic and gaming benchmarks, and its leadership in our ranking turned out to be quite predictable. In other words, the general table with the rating of video cards by performance is good, but our opinion is that when choosing the best video card for a home PC, you should not chase conditional parrots. It is necessary to evaluate video cards as a whole, buying not the fastest, but the most suitable models for your goals. If you feel the same way, the next part of the article is for you. If you’re serious about graphics quality, if you like heavy titles and prefer 4K gaming, then you should definitely opt for the Nvidia GeForce RTX 3080 — in our opinion, the best graphics card of 2021 and 2022. Of course, in terms of pure performance, the GeForce RTX 3080 is inferior to the GeForce RTX 3080 Ti and RTX 3090, but this video card is much more affordable than its counterparts, offering a much more interesting price-performance ratio. The whole question is whether you need such speed. For the same Full HD gaming, it is clearly redundant, and if you do not plan to buy a monitor with a higher resolution, you better opt for more affordable solutions. From what we’ve written, you might be under the impression that the GeForce RTX 3090 Ti is an overpriced graphics card built solely to shine in benchmarks. But in fact, this is not at all the case, and she also entered our top graphics cards of 2021 and 2022. Yes, it is not at all profitable to buy it for games and entertainment, but the GeForce RTX 3090 Ti is indispensable when it comes to professional use. With NVLink support, the graphics card is extremely efficient in professional applications and GPU computing. For example, in the same Blender, it is 35% faster than the GeForce RTX 3080 and more than doubles the Titan RTX. But most importantly, unlike professional accelerators, the RTX 3090 Ti is an all-in-one solution that excels at both work and gaming at any level. Purchase The best video cards for gaming in FHD, 2K and 4K: what, how much and why is it so expensive The 2021-2022 GPU performance ranking continues with the GeForce RTX 3060 Ti. Video card for only 9% slower than the GeForce RTX 3070, but at the same time cheaper by 20%. It handles 1440p gaming with ease, offering the full range of features and technologies of the RTX 30xx series, but at a low cost. The main problem with the Nvidia GeForce RTX 3060 Ti is the limited amount of video memory. Its 8 GB is enough for most games for now, but the most advanced titles are already starting to go beyond this threshold, and the RTX 3060 Ti may become obsolete much sooner than you expected. However, in this case, there is a GeForce RTX 3060 12GB. It’s built on a GA106 GPU with a quarter fewer cores than the RTX 3060 Ti and will never be able to match it in terms of overall performance, but the graphics card has a lot more memory and a lower price. The relatively high price tag does not yet allow the Nvidia GeForce RTX 3050 to be classified as a budget video card, but it is still cheaper than other representatives of the series, while providing quite decent Full HD gaming with tracing rays and DLSS support. And although it is 7% slower than the previous generation RTX 2060, we would rather buy the RTX graphics card than pay the same amount for the GeForce GTX 1660 Super. If you don’t need ray tracing, we suggest AMD Radeon RX 6600. It is only slightly more expensive than RTX 3050, while offering 30% better performance in games at Full HD resolution at maximum graphics settings. Computers Best NVIDIA graphics cards to buy in 2021 When we talk about budget graphics cards, we often mean some old models with outdated technologies. But not in this case. The Radeon RX 6500 XT uses the Navi 24 graphics processor on the modern RDNA 2 microarchitecture. The low-cost status of the video card here is manifested in the memory bus cut to 64 bits, a small amount of Infinity Cache and support for the old video codec. Purchase Do you need a discrete graphics card or is integrated graphics sufficient? However, the AMD Radeon RX 6500 XT is rightfully included in our GPU performance rating. See also Tags video cards Author Dmitry Mukharev Was the article interesting? Share link By clicking on the «Subscribe» button, Recommended Advertising on CHIP
Author Anatoly Vorontsov Reading 7 min. Views 105 Posted Hello everyone! In this review, I picked up the 7 best video adapters for gaming from NVidia today. Prices for video cards are falling rapidly and even if they are still far from low or recommended, but compared to what it was a couple of months ago, the situation has become much better. And due to discounts in some stores, you can get great options for your money. Contents NVidia GeForce RTX 3050
I decided to start with a budget novelty in the face of the RTX 3050. If you need something as budget-friendly as possible, but still quite peppy, then you can look towards the previous generation, for example, on the GTX 1660 Super. The RTX 3060 Ti is an average card in the lineup, but even it is able to provide gameplay at the highest level. In terms of price-performance ratio, this is one of the best green mill solutions. Step back a little and meet another member of the Turing family in the form of the GTX 1660 Ti. I will not dwell on this adapter for a long time, because in fact it is a slightly faster GTX 1660 Super, which I considered a little earlier. Moving on, building up power, and here we are met by the pre-top model of the current line — RTX 3070. In fact, this card was created in order to play absolutely everything here and now in 4K and with ultra-graphics settings with sixty frames or more. In QuadHD, the adapter delivers even under 100 frames, which will appeal to fans of monitors with a high refresh rate. At the same time, you can find the RTX 3070 today for extremely sane money, given its capabilities. However, if you’re looking for a 4K ultra card that will last for years to come, then this might not be your option. Finally, I left a couple of tops among the tops and the first I suggest considering the RTX 3080 Ti. For games, this is a real flagship, and if you want maximum comfort, but within reason, then it’s better to take it anyway. The card is equipped with a top-end chip and twelve gigabytes of high-speed GDDR6X video memory, which will last for many more years of playing 4K at ultras, with beams and a frame rate far beyond 60 frames per second. This is exactly the card you need to stock up for the future without having to lower your settings. It costs, of course, not a little, but flagships have never been famous for low prices. However, the cost per frame on the RTX 3080 Ti is far from the highest. If you don’t use words like «limited budget» in one sentence and prefer to make the most of life, then the RTX 3090 is for you. With a crazy 24 GB video buffer, this card will not experience problems in high resolution with high-quality textures for a very long time. However, even in the 3080, TiNVidia squeezed almost all the juice out of the GA102 chip, which is also used in the RTX 3090. In the end, it is not much more powerful here and the differences in games are sometimes so small that they can be attributed to an error. That’s why I said that if you are counting on reasonable spending, then it is better to limit yourself to the 3080 Ti. But, again, for wealthy RTX 309 connoisseurs0 will be a faithful companion for many years to come. In the direction of fresh and hot in every sense of the RTX 3090Ti, I have not yet looked. If it appears in our stores, then so far only in large cities and in single copies. And it justifies its cost and power consumption even less than a simple 3090. We bring to your attention a translation of an article published by Techspot, the authors of which analyze the video card market and recommend the best of them for purchase. In their opinion, buying a new high-end graphics card may not be a good idea, as these products will replace newer and faster GPUs before the end of the year. However, if you are looking for something in the middle price range, then it will most likely take some time before these cards are updated. It also makes sense to buy if you do not want to wait until acceptable prices for new generation video cards are established. Let’s be honest, prices are almost always inflated at launch, and new product availability can also be very weak during the first few months after launch. Six games were selected for testing: Red Dead Redemption 2, Rainbow Six Siege, Far Cry 6, Hitman 3, Dying Light 2 (medium settings), Shadow of the Tomb Raider (high quality). We use medium quality settings to show both entry and high quality products in one table. Modern entry-level cards such as the RX 6500 XT are not designed for gaming at high quality settings, so medium quality is the maximum for these cards. And top-tier models usually work great at medium settings, although many will choose to play using the Ultra preset. We also have some 4K data that will be most useful for high-end cards. All testing was done using a Ryzen 7 5800X3D with DDR4-3600 CL16 memory and Resizable BAR enabled, a feature that perfectly minimizes certain CPU weaknesses, especially when testing at 1080p. Course Frontend Operate HTML, CSS and JavaScript and get the job done REGISTER! Zmist AMD Radeon RX 6600: Its cost per frame is 7% better than the Radeon 6600 XT (which is in second place). The RTX 3050, which now costs $330 and sits between the RX 6600 and RX 6600 XT, could also be in this battle of entry-level cards. However, the price per frame for the GeForce model is 43% more expensive than the 6600 and 33% more expensive than the 6600 XT, which is not very justified. The RTX 3050 remains a poor investment despite price cuts over the past few months. Much more appropriate to compare with the $380 RTX 3060. In April, the price per frame of this card was 22% more expensive than the 6600 XT, and now it is only 13%. This makes the RTX 3060 a good buy for 1080p gaming. Playing at 1440p, we can compare top-end models, though it doesn’t change the overall placement of each card much (compared to 1080p). The RX 6600 is still the best GPU in terms of frame cost, but the RX 6700 XT is surprisingly close to it and only 4% more expensive. These two cards are not on the same level, they have a difference in performance, but this data suggests that the 6700 XT is an excellent buy for about $500. Of course, some may point out the lack of certain features in the 6700 XT, such as the lack of DLSS, weaker support for ray tracing, not up to Nvidia solutions. The RTX 3060 Ti is only 12% more expensive per frame; it’s slightly slower than the 6700 XT at 1440p, and also costs $30 more. We think many gamers at this price point will want access to Nvidia features, at least until FSR 2.0 can catch up with DLSS. Thanks to lower prices for Nvidia products, it is now more difficult to choose in higher market segments. AMD used to rank slightly lower than competing Nvidia models, but that’s no longer the case. The 6800 XT and RTX 3070 have the same cost per frame, while models up to the RTX 3080 are within 15% of the 6800 XT. Depending on how important Nvidia features are to you, it might make sense to choose the RTX 3080 over AMD products. If you’re looking for the closest Nvidia card to the 6800 XT in terms of rasterization performance, it’s the RTX 3080 Ti, which is now 37% more expensive per frame. We certainly wouldn’t recommend this or any other top-of-the-line model in Nvidia’s current lineup. But given the RTX 3080 12GB and below, we think it makes sense to choose a green team representative as Nvidia’s GPUs have become more competitive in recent months. 
The only problem is that its little sister RTX 2070 Super is almost as good in terms of price and power, so sometimes you might wonder why the RTX 2080 Super is needed? NVIDIA GeForce RTX 2070 SUPER
And considering the fact that the 2070 costs a couple of hundred dollars less than the 2080, you can imagine what a bargain this is. NVIDIA GeForce RTX 3060
In any case, this is a good «folk» map, which you will not have problems with most current AAA titles. NVIDIA GeForce RTX 2060 SUPER
NVIDIA GeForce RTX 3050
NVIDIA GeForce GTX 1660 TI
However, given the small number of games that really use ray tracing, this loss becomes not so significant. And it becomes even smaller if you remember at what cost for PC performance all this beauty is given. NVIDIA GeForce GTX 1660
For now. NVIDIA GeForce GTX 1650 SUPER
A consolation can be the impressive power efficiency of the graphics card, which gives room for creating quiet and economical gaming builds. NVIDIA GeForce GTX 1050 Ti
AMD
AMD Radeon RX 6900 XT
AMD Radeon RX 6800 XT
The video card is low-noise, supports the HDMI 2.1 standard, gives a performance boost when used with AMD Ryzen 5000 family processors — an excellent solution for enthusiasts, especially considering the democratic price. AMD Radeon RX 6700 XT
These are impressive figures, but only if you forget about ray tracing, where the «red» cards are traditionally in the laggard position, even though this model is equipped with hardware support for RT. AMD Radeon RX 6600 XT
It makes no sense to talk about something more serious, but the video card does not pretend to be: AMD did not declare that the RX 6600 XT would show itself worthy, for example, in 4K. AMD Radeon RX 5700 XT
Yes, the Nvidia card is more powerful, but the difference is incredibly small. AMD Radeon RX 6500 XT
AMD Radeon RX 5700
AMD Radeon RX 5600 XT
Its main advantage is the new RDNA architecture based on the 7nm process technology, due to which gamers can expect impressive results in DX12 applications, where the video card confidently outperforms its competitor from the «green» camp — NVIDIA GeForce RTX 2060. AMD Radeon RX 5500 XT
In the budget segment, a lot depends on the price, and the AMD Radeon RX 5500 XT is ready to tear and throw, pushing the competition. AMD Radeon RX 590
AMD Radeon RX 580
304 | Memory – 8GB GDDR5 | Bus — 256-bit
AMD Radeon RX 570
There is an 8GB version of the RX 570 on the market, however, the extra 4 GB mark-up brings it very close to the cost of the RX 580, which now, we must admit, looks very attractive. How to choose a gaming graphics card?
The higher the resolution, the more powerful graphics card you will need; the same is true for those who like to move all the graphic settings sliders to the right. In turn, if you plan to play undemanding network titles, you can think about a budget video card or a video chip (APU) built into the processor. 
Also pay attention to the dimensions of the video adapter, otherwise you may encounter difficulties when trying to install it in a PC case. Graphics Card Performance Ranking 2022 : Comparison Chart
When choosing a video card, you should definitely take into account the characteristics of your computer, what resolution you plan to play or work in, why you buy a video card, what means you have. And many many others. Contents
Model
GPU
Memory
Power consumption
Nvidia GeForce RTX 3090 Ti
GA102
24 GB GDDR6X
450 W
AMD Radeon RX 6900 XT
Navi 21
16 GB GDDR6
300W
Nvidia GeForce RTX 3090
GA102
24 GB GDDR6X
350W
Nvidia GeForce RTX 3080 12GB
GA102
12 GB GDDR6X
400 W
AMD Radeon RX 6800 XT
Navi 21
16 GB GDDR6
300W
Nvidia GeForce RTX 3080 Ti
GA102
12 GB GDDR6X
350 W
Nvidia GeForce RTX 3080
GA102
10 GB GDDR6X
320 W
AMD Radeon RX 6800
Navi 21
16 GB GDDR6
250 W
Nvidia GeForce RTX 3070 Ti
GA104
8 GB GDDR6X
290 W
Nvidia Titan RTX
TU102
24 GB GDDR6
280 W
Nvidia GeForce RTX 3070
GA104
8 GB GDDR6
220 W
AMD Radeon RX 6700 XT
Navi 22
12 GB GDDR6
230 W
Nvidia GeForce RTX 2080 Ti
TU102
11 GB GDDR6
250 W
Nvidia GeForce RTX 3060 Ti
GA104
8 GB GDDR6
200 W
Nvidia GeForce RTX 2080 Super
TU104
8 GB GDDR6
250 W
Nvidia GeForce RTX 2080
TU104
8 GB GDDR6
215 W
AMD Radeon RX 6600 XT
Navi 23
8 GB GDDR6
160W
Nvidia GeForce RTX 2070 Super
TU104
8 GB GDDR6
215 W
AMD Radeon RX 5700 XT
Navi 10
8 GB GDDR6
225 W
Nvidia GeForce RTX 3060
GA106
12 GB GDDR6
170 W
AMD Radeon VII
Vega 20
16 GB HBM2
300W
Nvidia GeForce RTX 2070
TU106
8 GB GDDR6
175 W
AMD Radeon RX 6600
Navi 23
8 GB GDDR6
132 W
Nvidia GeForce GTX 1080 Ti
GP102
11 GB GDDR5X
250 W
Nvidia GeForce RTX 2060 Super
TU106
8 GB GDDR6
175 W
AMD Radeon RX 5700
Navi 10
8 GB GDDR6
180 W
AMD Radeon RX 5600 XT
Navi 10
8 GB GDDR6
160W
AMD Radeon RX Vega 64
Vega 10
8 GB HBM2
295 W
Nvidia GeForce RTX 2060
TU106
6 GB GDDR6
160W
Nvidia GeForce GTX 1080
GP104
8 GB GDDR5X
180 W
Nvidia GeForce RTX 3050
GA106
8 GB GDDR6
130W
Nvidia GeForce GTX 1070 Ti
GP104
8 GB GDDR5
180 W
AMD Radeon RX Vega 56
Vega 10
8 GB HBM2
210W
Nvidia GeForce GTX 1070
GP104
8 GB GDDR5
150 W
Nvidia GeForce GTX 1660 Super
TU116
6 GB GDDR6
125 W
Nvidia GeForce GTX 1660 Ti
TU116
6 GB GDDR6
120 W
Nvidia GeForce GTX 1660
TU116
6 GB GDDR5
120 W
AMD Radeon RX 5500 XT 8GB
Navi 14
8 GB GDDR6
130W
AMD Radeon RX 590
Polaris 30
8 GB GDDR5
225 W
Nvidia GeForce GTX 980 Ti
GM200
6 GB GDDR5
250 W
AMD Radeon R9 Fury X
4 GB HBM2
275 W
AMD Radeon RX 580 8GB
Polaris 20
8 GB GDDR5
185 W
AMD Radeon RX 5500 XT 4GB
Navi 14
4 GB GDDR6
130W
Nvidia GeForce GTX 1650 Super
TU116
4 GB GDDR6
100 W
Nvidia GeForce GTX 1060 6GB
GP106
6 GB GDDR5
120 W
AMD Radeon RX 6500 XT
Navi 24
4 GB GDDR6
107W
AMD Radeon R9390
Grenada
8 GB GDDR5
275 W
Nvidia GeForce GTX 980
GM204
4 GB GDDR5
165W
AMD Radeon RX 570 4GB
Polaris 20
4 GB GDDR5
150 W
Nvidia GeForce GTX 1060 3GB
GP106
3 GB GDDR5
120 W
Nvidia GeForce GTX 1650
TU117
4 GB GDDR5
75W
Nvidia GeForce GTX 970
GM204
4 GB GDDR5
145 W
Nvidia GeForce GTX 780
GK110
3 GB GDDR5
230W
Nvidia GeForce GTX 1050 Ti
GP107
4 GB GDDR5
75W
Nvidia GeForce GTX 1050
GP107
2 GB GDDR5
75W
AMD Radeon RX 560 4GB
Baffin
4 GB GDDR5
60-80W
AMD Radeon RX 550 4GB
Lexa
4 GB GDDR5
50W
The real performance of video cards when mining Ethereum is constantly changing, and often not for the better. Their payback depends on the cost of electricity in your region, the algorithms and optimizations that you carry out, and, of course, on the current prices for video cards, which are also constantly jumping.
Model
Payback, days
Nvidia GeForce GTX 1060 6GB
393
AMD Radeon RX 570 8GB
418
Nvidia GeForce GTX 1080
422
Nvidia GeForce GTX 1070
423
AMD Radeon RX 5600 XT
426
AMD Radeon RX 5500 XT 8GB
437
Nvidia GeForce RTX 3060
439
Nvidia GeForce RTX 3060 Ti
441
AMD Radeon RX 5700 XT
449
AMD Radeon RX 580 8GB
451
Nvidia GeForce RTX 2060 Super
457
Nvidia GeForce RTX 2070
458
AMD Radeon RX 5700
459
Nvidia GeForce GTX 1660 Ti
465
Nvidia GeForce GTX 1070 Ti
467
AMD Radeon RX 590
469
Nvidia GeForce GTX 1660
488
Nvidia GeForce GTX 1660 Super
497
Nvidia GeForce RTX 2060
498
Nvidia GeForce RTX 2070 Super
499
Nvidia GeForce GTX 1080 Ti
506
Nvidia GeForce RTX 3080
512
Nvidia GeForce RTX 3070
516
Nvidia GeForce RTX 2080
526
AMD Radeon RX Vega 64
531
AMD Radeon RX 6800
541
AMD Radeon VII
542
AMD Radeon RX 6700 XT
544
AMD Radeon RX Vega 56
550
AMD Radeon RX 6600
552
AMD Radeon RX 6600 XT
563
Nvidia GeForce RTX 2080 Super
580
Nvidia GeForce RTX 2080 Ti
587
Nvidia GeForce RTX 3060 Ti LHR
609
AMD Radeon RX 6800 XT
609
Nvidia GeForce RTX 3060 LHR
616
Nvidia GeForce RTX 3090
683
Nvidia GeForce RTX 3070 LHR
715
Nvidia GeForce RTX 3070 Ti LHR
726
AMD Radeon RX 6900 XT
731
Nvidia GeForce RTX 3080 LHR
745
Nvidia GeForce RTX 3050 LHR
748
Nvidia GeForce RTX 3080 Ti LHR
754
However, the graphics card is almost twice as expensive as the AMD Radeon RX 6900 XT and consumes 50% more power, while remaining only marginally faster than AMD’s design. In other words, the advantage you get when buying an RTX 3090 Ti is nothing compared to the amount you have to pay for it.
Category
Model
Best graphics card overall
Nvidia GeForce RTX 3080
Best for professionals
Nvidia GeForce RTX 3090 Ti
Best for 1440p gaming
Nvidia GeForce RTX 3060 Ti
Best for Full HD gaming
Nvidia GeForce RTX 3050
Best budget
AMD Radeon RX 6500 XT
Best graphics card overall: Nvidia GeForce RTX 3080
It is she who can be called the shadow gaming flagship of Nvidia, with all the ensuing consequences. Best for Pros: Nvidia GeForce RTX 3090 Ti
Best for 1440p gaming: Nvidia GeForce RTX 3060 Ti
Best for Full HD gaming: Nvidia GeForce RTX 3050
Best Budget: AMD Radeon RX 6500 XT
The cost of the video card makes it much more attractive than most competitors. But more importantly, it is much easier to find at an adequate price compared to the same GTX 1650 Super.
you consent to the processing of personal data
Contacts TOP-7. The best NVIDIA graphics cards for gaming.
June 2022. Rating!
Updated
start of sales due to the general hype in the market. Apart from this, the card turned out to be quite good. This is the starter solution of the Ampere family and even it already allows you to try beams and take advantage of all the delights of DLSS. Let me remind you that the youngest model of those that could boast of the presence of tensor and RT cores in the last generation was the average and by no means the cheapest RTX 2060. In addition to hardware support for all fashionable technologies, the RTX 3050 boasts an impressive 8 GB video buffer on GDDR6 chips. Such a set will last for many years without focusing on video memory. As for performance in general, the card pulls everything at high and even ultra-settings in FullHD resolution. And with the help, again, of DLSS, you can already swing at QuadHD in many games.
Today this vidyahu can be purchased cheaper than the same 3050 and at the same time you get a very lively video adapter with good performance. Due to the six-gigabyte video buffer, the card still feels great in all modern projects, without experiencing an acute shortage of memory. The chip also takes out all modern toys at least at medium 1080p resolution. And if you spend 5-10 minutes and experiment with the settings, you can achieve a picture at the level of high and ultra in most games. The potential of the GTX 1660 Super will last for another couple of years at least before you have to reduce the settings to the minimum everywhere. The only disadvantage of video is the lack of hardware support for beams and DLSS. But if that doesn’t bother you, then the 1660 Super is a great choice!
The 3060 Ti today exports all projects in QuadHD resolution, and even for 4K it is enough. Only in some games will you have to lower a couple of points from ultra to high. Well, or you can just activate DLSS and thereby raise the FPS almost 2 times. But, again, even without it, in many projects you will be waiting for 60 frames per second in 4K and on ultras. The only thing that is not entirely clear in this card is the amount of video memory. For some reason, NVidia gave the younger RTX 3060 12 gigabytes of memory, while the Ti version received only 8 gigabytes, like the very initial RTX 3050. In the future, this will definitely affect the potential of the card, but on the other hand, today and in the next couple of years this will be enough for absolutely any projects.
The differences are minor, except perhaps for more CUDA cores and a half increase in memory bandwidth. Still, it’s a card worth checking out today if you can find it for less than the GTX 1660 Super. And with what kind of mess has been happening with price tags lately, this situation is quite real. So if you see Ti cheaper or for the same money as Super, then take Ti without hesitation — you won’t lose. 
Deprived of eight gigabytes of video memory, the vidyaha will soon begin to choke in 4K resolution and with high-quality textures. DLSS will smooth out this process, but it will not be able to get rid of it. But today it is the best option for the most comfortable gaming for your money.
GeForce vs. Radeon: the best video cards of mid-2022
We will not consider each game separately, but we will use the average data calculated using the geomean function. This gives us an understanding of the performance of each card in order to determine the «cost per frame».
Best 1080p Gaming Graphics Card
The 6500 XT comes in third, though given the low performance levels and limited feature set, this card should have offered a better price-per-frame to make up for it. Although the price has dropped to $180 (which is below MSRP), to match the cost of a 6600 frame, it would need to cost no more than $160, as the RX 6400 is now. As we said, the price should be no more than $150 , and best of all — about 100 dollars. 
If you’re not interested in DLSS, which isn’t very efficient at 1080p, the 6600 XT is a better choice. Best graphics card for 1440p gaming
Best graphics card for 4K gaming
When it comes to 4K gaming, we see Nvidia’s RTX 30 GPUs win as their performance scales better at higher resolutions than AMD’s.
But the RX 6700 XT is the undisputed leader in frame price, the 3060 Ti is also at the top of the chart, costing 8% more than AMD. That’s more than in spring, but still quite a bit, especially if Nvidia’s feature set is important to you.
With this resolution, high-end cards are most interesting, especially those providing an average of more than 90 fps. The best GPU here is the RX 6800 XT, but as we’ve seen at 1440p, GeForce products are closer to the lead this month than they’ve been in the past. The
The
RTX 3080 is only 5% more expensive per frame (up 13% in April), so it’s hard not to notice Nvidia offering additional features in such a fight. The fight between the RTX 3080 Ti and the RX 6900 XT has also become more dramatic, with GeForce being 19% more expensive per frame before, and that forced buying Radeon cards. And now the “price per frame” is only 11% higher and this complicates the choice.
What hasn’t changed is that Nvidia’s flagship GPUs are terribly expensive.
The RTX 3090, and especially the RTX 3090 Ti, are slightly faster than the RTX 3080 Ti but cost 58% more per frame (in the case of the 3090 Ti). While a large VRAM buffer is useful for some workstation applications, it is very difficult to justify the 3090 series for gaming.
Best Graphics Card for 1440p Gaming (Europe)
In Europe, prices are more favorable to AMD. As in the US, the RX 6600 is the best GPU on the market, but there are four more AMD cards ahead of Nvidia’s first model, including the RX 6800 XT. Therefore, it is difficult to recommend a GeForce GPU. For example, the 6600 is 10% slower than the RTX 3060 but costs 21% less per frame: you save over 100 euros by buying a Radeon. Therefore, the 6600 is in a better position in the mainstream market than in the US, although the RTX 3050 looks better in Europe (but its price is still not very satisfactory).
For mid-rangers, the RX 6700 XT is positioned similarly to the US market when compared to the RTX 3060 Ti, but the GeForce costs 12% more than a frame.
However, it’s hard to justify spending above €500 on any of these cards, even the RTX 3070. The only exception is the RX 6800 XT: at a frame price of under €5, it’s the undisputed choice for buyers in need of high-quality frame rates. The closest-performing cards from Nvidia start with the RTX 3080, and that model is 28% more expensive, which is hard to justify even considering the difference in features. Even worse with higher tier models like the RTX 3080 Ti; especially ridiculous RTX 3090 Ti.
Conclusions
In summary, there are two groups of GPUs on the market that should be avoided if cost matters: VRAM buffer.
And the RTX 3090 and RTX 3090 Ti should be avoided for another reason. Now they offer the worst value on the market for gamers and by the end of 2022 they will be swept away by a new generation of GPUs.
As for the cards that can be considered for purchase, this will depend not only on the indicators (see diagrams), but also on your region.
There are a few instances where Nvidia has closed the frame cost gap compared to AMD cards, but still remains about 10% more expensive in this metric. If you’re interested in DLSS and ray tracing it’s more than worth it, but if you’re not, then AMD cards tend to have the best cost/performance ratio.
| №1 | NVIDIA GeForce RTX 3090 Ti | Type desktop | Productivity100.00 | ArchitectureAmpere | Year of manufacture2022 | Price now1488 USD | TDP450 W |
| #2 | AMD Radeon RX 6950 XT | Type Desktop | Performance95.27 | ArchitectureNavi / RDNA2 | Year of manufacture2022 | Price now1079 USD | TDP335 W |
| #3 | NVIDIA GeForce RTX 3080 Ti | Type Desktop |
Performance92. 24 |
ArchitectureAmpere | Year of manufacture2020 | Price now1289 USD | TDP350 W |
| #4 | NVIDIA GeForce RTX 3090 | Type Desktop | Performance90.06 | ArchitectureAmpere | Year of manufacture2020 | Price now1268 USD | TDP350 W |
| #5 | NVIDIA GeForce RTX 3080 12 GB | Type Desktop | Performance88.08 | ArchitectureAmpere | Year of manufacture2022 | Price now820 USD | TDP350 W |
| #6 | AMD Radeon RX 6900 XT | Type Desktop | Capacity87.60 | ArchitectureNavi / RDNA2 | Year of manufacture2020 | Price now945 USD | TDP300 W |
| #7 | NVIDIA GeForce RTX 3080 | Type Desktop |
Capacity85. 50 |
ArchitectureAmpere | Year of manufacture2020 | Price now846 USD | TDP320 W |
| #8 | NVIDIA RTX A5500 | Type Desktop | Capacity81.22 | ArchitectureAmpere | Year of release2022 | Price now4593 USD | TDP230 W |
| #9 | AMD Radeon RX 6800 XT | Type Desktop | Capacity80.88 | ArchitectureNavi / RDNA2 | Year of manufacture2020 | Price now646 USD | TDP300 W |
| #10 | NVIDIA GeForce RTX 3070 Ti | Type Desktop | Performance79.94 | ArchitectureAmpere | Year of manufacture2021 | Price now668 USD | TDP290 W |
| #11 | NVIDIA RTX A5000 | Workstation type |
Performance79. 79 |
ArchitectureAmpere | Year of manufacture2021 | Price now3652 USD | TDP230 W |
| #12 | NVIDIA GeForce RTX 3070 | Type Desktop | Performance75.39 | ArchitectureAmpere | Year of manufacture2020 | Price now583 USD | TDP220 W |
| #13 | NVIDIA GeForce RTX 2080 Ti | Type Desktop | Performance73.97 | ArchitectureTuring | Year of manufacture2018 | Price now823 USD | TDP270 W |
| #14 | AMD Radeon RX 6850M XT | Notebook Type | Performance72.10 | ArchitectureRDNA 2 | Year of manufacture2022 | Price now − | TDP145 W |
| #15 | NVIDIA RTX A4500 | Workstation type |
Capacity71. 33 |
ArchitectureAmpere | Year of manufacture2021 | Price now2503 USD | TDP200 W |
| #16 | AMD Radeon RX 6800 | Type desktop | Capacity70.77 | ArchitectureNavi / RDNA2 | Year of manufacture2020 | Price now629 USD | TDP250 W |
| #17 | NVIDIA GeForce RTX 3080 Ti Laptop GPU | Notebook Type | Performance69.76 | ArchitectureAmpere | Year of manufacture2022 | Price now − | TDP150 W |
| #18 | NVIDIA GeForce RTX 3060 Ti | Type Desktop | Capacity69.03 | ArchitectureAmpere | Year of manufacture2020 | Price now497 USD | TDP220 W |
| #19 | AMD Radeon RX 6700 | Type Desktop |
Capacity66. 52 |
ArchitectureRDNA 2.0 | Year of manufacture2021 | Price now512 USD | TDP175 W |
| #20 | NVIDIA Quadro GV100 | Type for workstations | Capacity66.37 | ArchitectureVolta | Year of manufacture2018 | Price now6989 USD | TDP250 W |
| #21 | NVIDIA Quadro RTX 6000 | Workstation type | Performance66.32 | ArchitectureTuring | Year of manufacture2018 | Price now3983 USD | TDP260 W |
| #22 | NVIDIA GeForce RTX 2080 Super | Type Desktop | Performance66.11 | ArchitectureTuring | Year of manufacture2019 | Price now412 USD | TDP250 W |
| #23 | AMD Radeon RX 6750 XT | Type Desktop |
Productivity66. 05 |
ArchitectureNavi / RDNA2 | Year of manufacture2022 | Price now567 USD | TDP250 W |
| #24 | NVIDIA TITAN Xp | Type Desktop | Performance65.92 | ArchitecturePascal | Year of manufacture2017 | Price now216 USD | TDP250 W |
| #25 | NVIDIA Quadro RTX A6000 | Type for workstations | Capacity65.47 | ArchitectureAmpere | Year of manufacture2020 | Price now10949 USD | TDP300 W |
| #26 | AMD Radeon Pro W6800 | Workstation type | Capacity64.85 | ArchitectureNavi / RDNA2 | Year of issue2021 | Price now2800 USD | TDP250 W |
| #27 | NVIDIA Quadro RTX 8000 | Workstation type |
Performance64. 79 |
ArchitectureTuring | Year of manufacture2018 | Price now4377 USD | TDP260 W |
| #28 | NVIDIA GeForce GTX 1080 SLI Mobile | Notebook Type | Capacity64.78 | ArchitecturePascal | Year of manufacture2016 | Price now352 USD | TDP− |
| #29 | AMD Radeon RX 6700 XT | Type Desktop | Performance64.43 | ArchitectureNavi / RDNA2 | Year of manufacture2021 | Price now458 USD | TDP230 W |
| #30 | NVIDIA RTX A4000 | Workstation Type | Performance64.17 | ArchitectureAmpere | Year of manufacture2021 | Price now2026 USD | TDP140 W |
| #31 | NVIDIA TITAN RTX | Type Desktop |
Capacity63. 88 |
ArchitectureTuring | Year of manufacture2018 | Price now1686 USD | TDP280 W |
| #32 | NVIDIA GeForce RTX 2080 | Type Desktop | Capacity63.54 | ArchitectureTuring | Year of manufacture2018 | Price now747 USD | TDP215 W |
| #33 | NVIDIA A10G | Type Desktop | Capacity63.42 | ArchitectureAmpere | Year of manufacture2021 | Price now79 USD | TDP150 W |
| #34 | NVIDIA GeForce RTX 3070 Ti Laptop GPU | Notebook Type | Capacity62.78 | ArchitectureAmpere | Year of manufacture2022 | Price now − | TDP125 W |
| #35 | NVIDIA GeForce GTX 1080 Ti | Type Desktop |
Capacity62. 29 |
ArchitecturePascal | Year of manufacture2017 | Price now486 USD | TDP250 W |
| #36 | NVIDIA RTX A5500 Laptop GPU | Notebook Type | Productivity61.90 | ArchitectureAmpere | Year of manufacture2022 | Price now − | TDP165 W |
| #37 | NVIDIA GeForce RTX 2070 Super | Type Desktop | Capacity61.59 | ArchitectureTuring | Year of manufacture2019 | Price now626 USD | TDP215 W |
| #38 | NVIDIA RTX A4500 Laptop GPU | Type for laptops | Capacity61.26 | ArchitectureAmpere | Year of manufacture2022 | Price now − | TDP140 W |
| #39 | NVIDIA GeForce RTX 3080 Mobile | Notebook Type |
Capacity60. 98 |
ArchitectureAmpere | Year of issue2021 | Price now − | TDP150 W |
| #40 | NVIDIA GeForce GTX 1070 SLI | Type Desktop | Performance58.36 | ArchitecturePascal | Year of manufacture2016 | Price now238 USD | TDP300 W |
| #41 | NVIDIA TITAN V | Type Desktop | Performance58.01 | ArchitectureVolta | Year of manufacture2017 | Price now528 USD | TDP250 W |
| #42 | NVIDIA GeForce RTX 3060 | Type desktop | Performance57.74 | ArchitectureAmpere | Year of manufacture2021 | Price now423 USD | TDP170 W |
| #43 | NVIDIA TITAN V CEO Edition | Type desktop |
Performance57. 54 |
ArchitectureVolta | Year of manufacture2018 | Price now1630 USD | TDP250 W |
| #44 | AMD Radeon RX 5700 XT | Type Desktop | Performance57.25 | ArchitectureNavi / RDNA | Year of manufacture2019 | Price now422 USD | TDP225 W |
| #45 | NVIDIA Tesla P40 | Workstation type | Performance57.13 | ArchitecturePascal | Year of manufacture2016 | Price now12 USD | TDP250 W |
| #46 | AMD Radeon Pro VII | Workstation type | Productivity57.09 | ArchitectureGCN 5.1 | Year of manufacture2020 | Price now2512 USD | TDP250 W |
| #47 | AMD Radeon VII | Type Desktop |
Performance56. 99 |
ArchitectureVega | Year of manufacture2019 | Price now218 USD | TDP295 W |
| #48 | AMD Radeon RX 5700 XT 50th Anniversary | Type desktop | Performance56.43 | ArchitectureRDNA 1.0 | Year of manufacture2019 | Price now409 USD | TDP225 W |
| #49 | NVIDIA GeForce RTX 2060 Super | Type Desktop | Productivity56.00 | ArchitectureTuring | Year of manufacture2019 | Price now288 USD | TDP175 W |
| #50 | AMD Radeon RX 6650 XT | Type Desktop | Performance55.98 | ArchitectureRDNA 2.0 | Year of manufacture2022 | Price now391 USD | TDP176 W |
| #51 | NVIDIA Quadro RTX 5000 | Workstation type |
Performance54. 77 |
ArchitectureTuring | Year of manufacture2018 | Price now2096 USD | TDP230 W |
| #52 | NVIDIA GeForce GTX 1070 SLI (Mobile) | Notebook Type | Performance54.63 | ArchitecturePascal | Year of manufacture2016 | Price now274 USD | TDP− |
| #53 | NVIDIA GeForce RTX 2070 | Type desktop | Performance54.53 | ArchitectureTuring | Year of manufacture2018 | Price now602 USD | TDP175 W |
| #54 | NVIDIA GeForce RTX 2070 Super Mobile | Notebook Type | Productivity54.38 | ArchitectureTuring | Year of manufacture2020 | Price now1443 USD | TDP115 W |
| #55 | AMD Radeon RX 6600 XT | Type Desktop |
Capacity53. 85 |
ArchitectureNavi / RDNA2 | Year of manufacture2021 | Price now621 USD | TDP160 W |
| #56 | Apple M1 8-Core GPU | Type for laptops | Performance53.68 | Architecture | Year of manufacture2020 | Price now − | TDP− |
| #57 | NVIDIA Quadro GP100 | Workstation type | Performance52.87 | ArchitecturePascal | Year of release2016 | Price now1969 USD | TDP235 W |
| #58 | NVIDIA Quadro RTX 4000 | Workstation type | Performance52.51 | ArchitectureTuring | Year of manufacture2018 | Price now2146 USD | TDP160 W |
| #59 | NVIDIA GeForce GTX 1080 | Type Desktop |
Performance51. 88 |
ArchitecturePascal | Year of manufacture2016 | Price now410 USD | TDP180 W |
| #60 | NVIDIA GeForce RTX 2080 Super Mobile | Notebook Type | Performance51.61 | ArchitectureTuring | Year of manufacture2020 | Price now1671 USD | TDP150W |
| #61 | NVIDIA GeForce RTX 2080 (Mobile) | Notebook type | Performance51.17 | ArchitectureTuring | Year of manufacture2019 | Price now2003 USD | TDP150 W |
| #62 | AMD Radeon Pro W5700 | Workstation type | Performance50.89 | ArchitectureRDNA 1.0 | Year of manufacture2019 | Price now1003 USD | TDP205 W |
| #63 | NVIDIA Quadro P6000 | Workstation Type |
Performance50. 53 |
ArchitecturePascal | Year of manufacture2016 | Price now2347 USD | TDP250 W |
| #64 | NVIDIA Quadro RTX 5000 (mobile) | Type for mobile workstations | Performance50.24 | ArchitectureTuring | Year of manufacture2019 | Price now3065 USD | TDP110 W |
| #65 | AMD Radeon Pro Vega II | Workstation type | Performance49.92 | ArchitectureGCN 5.1 | Year of manufacture2019 | Price now9999 USD | TDP475 W |
| #66 | NVIDIA Quadro RTX 5000 Max-Q | Mobile workstation type | Performance49.79 | ArchitectureTuring | Year of manufacture2019 | Price now2130 USD | TDP80 W |
| #67 | AMD Radeon RX Vega 64 | Type desktop |
Performance49. 66 |
ArchitectureVega | Year of manufacture2017 | Price now450 USD | TDP295 W |
| #68 | AMD Radeon RX 5700 | Type desktop | Performance49.61 | ArchitectureNavi / RDNA | Year of manufacture2019 | Price now473 USD | TDP180 W |
| #69 | AMD Radeon Pro Vega 64X | Workstation Type | Performance49.56 | ArchitectureGCN 5.0 | Year of manufacture2019 | Price now366 USD | TDP250 W |
| #70 | NVIDIA GeForce GTX 1070 Ti | Type Desktop | Productivity49.44 | ArchitecturePascal | Year of manufacture2017 | Price now293 USD | TDP180 W |
| #71 | NVIDIA GeForce RTX 3070 Mobile | Notebook Type |
Capacity48. 66 |
ArchitectureAmpere | Year of manufacture2021 | Price now − | TDP125 W |
| #72 | AMD Radeon Pro W6600 | Workstation Type | Performance48.62 | ArchitectureRDNA 2.0 | Year of manufacture2021 | Price now2077 USD | TDP100 W |
| #73 | AMD Radeon RX 6600 | Type desktop | Capacity48.44 | ArchitectureNavi / RDNA2 | Year of manufacture2021 | Price now314 USD | TDP132 W |
| #74 | NVIDIA GeForce RTX 2070 Super Max-Q | Notebook Type | Capacity48.27 | ArchitectureTuring | Year of manufacture2020 | Price now812 USD | TDP80 W |
| #75 | NVIDIA GeForce GTX 1080 Mobile | Type for Notebooks |
Performance47. 96 |
ArchitecturePascal | Year of manufacture2016 | Price now230 USD | TDP150 W |
| #76 | NVIDIA GeForce RTX 2080 Super Max-Q | Notebook Type | Performance47.47 | ArchitectureTuring | Year of release2020 | Price now812 USD | TDP90 W |
| #77 | NVIDIA GeForce RTX 2060 | Type Desktop | Performance47.44 | ArchitectureTuring | Year of manufacture2019 | Price now324 USD | TDP175 W |
| #78 | NVIDIA RTX A2000 12 GB | Type desktop | Performance47.33 | ArchitectureAmpere | Year of manufacture2021 | Price now1590 USD | TDP70 W |
| #79 | NVIDIA GeForce GTX 980 SLI (Mobile) | Notebook Type |
Performance47. 17 |
ArchitectureMaxwell | Year of manufacture2015 | Price now301 USD | TDP330 W |
| #80 | NVIDIA GeForce RTX 2080 Max-Q | Notebook Type | Performance47.06 | ArchitectureTuring | Year of manufacture2019 | Price now1268 USD | TDP80 W |
| #81 | AMD Radeon Pro WX 8200 | Workstation type | Performance47.02 | ArchitectureGCN 5.0 | Year of manufacture2018 | Price now2963 USD | TDP230 W |
| #82 | NVIDIA GeForce GTX 980 Ti | Type Desktop | Performance46.96 | ArchitectureMaxwell | Year of manufacture2015 | Price now471 USD | TDP250 W |
| #83 | AMD Radeon RX 5600 XT | Type Desktop |
Performance46. 87 |
ArchitectureRDNA 1.0 | Year of manufacture2020 | Price now302 USD | TDP150 W |
| #84 | AMD Radeon Vega Frontier Edition | Type Desktop | Capacity46.56 | ArchitectureGCN 5.0 | Year of release2017 | Price now961 USD | TDP300 W |
| #85 | AMD Radeon RX Vega 56 | Type desktop | Capacity46.20 | ArchitectureVega | Year of manufacture2017 | Price now350 USD | TDP210 W |
| #86 | AMD Radeon RX 6800S | Notebook type | Capacity45.74 | ArchitectureRDNA 2 | Year of manufacture2021 | Price now − | TDP100 W |
| #87 | NVIDIA GeForce GTX 1070 | Type Desktop |
Performance45. 71 |
ArchitecturePascal | Year of manufacture2016 | Price now329 USD | TDP150 W |
| #88 | AMD Radeon PRO WX 9100 | Workstation Type | Capacity45.13 | ArchitectureGCN 5.0 | Year of manufacture2017 | Price now2396 USD | TDP230 W |
| #89 | NVIDIA GeForce GTX TITAN X | Type Desktop | Performance44.88 | ArchitectureMaxwell 2.0 | Year of manufacture2015 | Price now406 USD | TDP250 W |
| #90 | NVIDIA RTX A2000 | Type Desktop | Performance44.13 | ArchitectureAmpere | Year of manufacture2021 | Price now1397 USD | TDP70 W |
| #91 | NVIDIA Titan X Pascal | Type Desktop |
Performance44. 12 |
ArchitecturePascal | Year of manufacture2016 | Price now620 USD | TDP250 W |
| #92 | NVIDIA Quadro RTX 4000 Mobile | Type Mobile Workstation | Performance43.49 | ArchitectureTuring | Year of manufacture2019 | Price now2890 USD | TDP110 W |
| #93 | NVIDIA Quadro P5200 | Mobile workstation type | Capacity43.34 | ArchitecturePascal | Year of manufacture2017 | Price now3894 USD | TDP150 W |
| #94 | NVIDIA GeForce GTX 1660 Super | Type desktop | Productivity43.21 | ArchitectureTuring | Year of manufacture2019 | Price now241 USD | TDP125 W |
| #95 | AMD Radeon RX 6700S | Notebook Type |
Performance43. 20 |
ArchitectureRDNA 2 | Year of manufacture2022 | Price now − | TDP80 W |
| #96 | NVIDIA GeForce RTX 3050 8 GB | Type desktop | Capacity42.72 | ArchitectureAmpere | Year of manufacture2022 | Price now458 USD | TDP130 W |
| #97 | AMD Radeon Pro 5700 XT | Workstation type | Performance42.52 | ArchitectureRDNA 1.0 | Year of manufacture2020 | Price now − | TDP130 W |
| #98 | NVIDIA GeForce RTX 3060 Mobile | Notebook Type | Performance42.51 | ArchitectureAmpere | Year of manufacture2021 | Price now − | TDP115 W |
| #99 | AMD Radeon Pro Vega 56 | Workstation type |
Performance41. 99 |
ArchitectureVega | Year of manufacture2017 | Price now4999 USD | TDP210 W |
| #100 | AMD Radeon RX 6700M | Notebook Type | Performance41.95 | ArchitectureRDNA 2 | Year of manufacture2020 | Price now − | TDP135 W |
| #101 | NVIDIA GeForce RTX 2070 (Mobile) | Notebook type | Performance41.85 | ArchitectureTuring | Year of manufacture2019 | Price now1758 USD | TDP115 W |
| #102 | Intel Arc A770M | Notebook type | Performance41.75 | ArchitectureXe HPG | Year of manufacture2022 | Price now − | TDP150 W |
| #103 | AMD Radeon Pro Vega 64 | Workstation type |
Capacity41. 64 |
ArchitectureGCN 5.0 | Year of manufacture2017 | Price now6074 USD | TDP250 W |
| #104 | NVIDIA Quadro M6000 24 GB | Type for workstations | Capacity41.47 | ArchitectureMaxwell 2.0 | Year of manufacture2016 | Price now877 USD | TDP250 W |
| #105 | NVIDIA RTX A5000 Mobile | Notebook Type | Capacity41.45 | ArchitectureAmpere | Year of manufacture2021 | Price now − | TDP165 W |
| #106 | NVIDIA Quadro P5000 | Workstation type | Performance40.37 | ArchitecturePascal | Year of manufacture2016 | Price now1431 USD | TDP180 W |
| #107 | AMD Radeon Pro 5700 | Workstation type |
Performance40. 12 |
ArchitectureRDNA 1.0 | Year of manufacture2020 | Price now696 USD | TDP130 W |
| #108 | NVIDIA GeForce GTX 1660 Ti | Type Desktop | Capacity40.07 | ArchitectureTuring | Year of manufacture2019 | Price now301 USD | TDP120 W |
| #109 | NVIDIA GeForce GTX 1660 | Type Desktop | Performance39.72 | ArchitectureTuring | Year of manufacture2019 | Price now326 USD | TDP120 W |
| #110 | NVIDIA Quadro M6000 | Workstation Type | Performance39.55 | ArchitectureMaxwell 2.0 | Year of manufacture2015 | Price now1489 USD | TDP250 W |
| #111 | NVIDIA Tesla M40 24 GB | Workstation type |
Performance39. 49 |
ArchitectureMaxwell 2.0 | Year of manufacture2015 | Price now370 USD | TDP250 W |
| #112 | NVIDIA Quadro P5000 Mobile | Type for mobile workstations | Capacity38.71 | ArchitecturePascal | Year of manufacture2017 | Price now2137 USD | TDP100 W |
| #113 | NVIDIA Quadro P4000 | Workstation type | Capacity38.65 | ArchitecturePascal | Year of release2017 | Price now715 USD | TDP105 W |
| #114 | NVIDIA GeForce RTX 2060 Mobile | Notebook Type | Capacity38.46 | ArchitectureTuring | Year of manufacture2019 | Price now1250 USD | TDP80 W |
| #115 | AMD Radeon Pro Vega 48 | Workstation type |
Capacity38. 45 |
ArchitectureGCN 5.0 | Year of manufacture2019 | Price now671 USD | TDP− |
| #116 | NVIDIA GeForce GTX 980 | Type Desktop | Capacity38.05 | ArchitectureMaxwell | Year of manufacture2014 | Price now331 USD | TDP220W |
| #117 | NVIDIA Quadro RTX 4000 Max-Q | Type for mobile workstations | Performance37.89 | ArchitectureTuring | Year of manufacture2019 | Price now − | TDP80 W |
| #118 | NVIDIA GeForce RTX 2070 Max-Q | Notebook Type | Productivity37.86 | ArchitectureTuring | Year of manufacture2019 | Price now1311 USD | TDP80 W |
| #119 | NVIDIA GeForce GTX 980M SLI | Notebook Type |
Performance37. 11 |
ArchitectureMaxwell | Year of manufacture2014 | Price now499 USD | TDP200 W |
| #120 | AMD Radeon RX 6600M | Type Notebook | Capacity37.05 | ArchitectureRDNA 2 | Year of manufacture2020 | Price now − | TDP100 W |
| #121 | NVIDIA GeForce RTX 3050 Ti Mobile | Notebook Type | Performance36.69 | ArchitectureAmpere | Year of manufacture2021 | Price now − | TDP60 W |
| #122 | NVIDIA Tesla T4 | Workstation Type | Performance36.58 | ArchitectureTuring | Year of manufacture2018 | Price now2405 USD | TDP70 W |
| #123 | NVIDIA GeForce RTX 3050 OEM | Type desktop |
Capacity36. 47 |
ArchitectureAmpere | Year of manufacture2022 | Price now − | TDP130 W |
| #124 | AMD Radeon RX 6650M | Notebook type | Performance36.34 | ArchitectureRDNA 2 | Year of manufacture2022 | Price now − | TDP120 W |
| #125 | NVIDIA RTX A3000 Mobile | Notebook Type | Capacity35.83 | ArchitectureAmpere | Year of manufacture2021 | Price now − | TDP130 W |
| #126 | AMD Radeon Pro SSG | Workstation type | Productivity35.56 | ArchitectureGCN 5.0 | Year of manufacture2017 | Price now996 USD | TDP350 W |
| #127 | NVIDIA GeForce GTX 1070 Mobile | Notebook Type |
Capacity35. 45 |
ArchitecturePascal | Year of manufacture2016 | Price now379 USD | TDP115 W |
| #128 | AMD Radeon RX 6800M | Type Notebook | Performance34.75 | ArchitectureRDNA 2 | Year of manufacture2021 | Price now − | TDP145 W |
| #129 | NVIDIA GeForce GTX 1060 6 GB | Type Desktop | Performance34.73 | ArchitecturePascal | Year of release2016 | Price now330 USD | TDP120 W |
| #130 | NVIDIA GeForce GTX 1080 Max-Q | Notebook Type | Performance34.58 | ArchitecturePascal | Year of manufacture2017 | Price now1008 USD | TDP90 W |
| #131 | NVIDIA GeForce GTX 1660 Ti Mobile | Notebook Type |
Performance34. 47 |
ArchitectureTuring | Year of manufacture2019 | Price now682 USD | TDP80 W |
| #132 | NVIDIA RTX A2000 Laptop GPU | Notebook Type | Capacity34.44 | ArchitectureAmpere | Year of manufacture2021 | Price now − | TDP95 W |
| #133 | AMD Radeon R9 FURY X | Type Desktop | Performance34.37 | ArchitectureGCN 3.0 | Year of manufacture2015 | Price now490 USD | TDP275 W |
| #134 | NVIDIA Tesla M40 | Workstation type | Performance34.27 | ArchitectureMaxwell 2.0 | Year of manufacture2015 | Price now151 USD | TDP250 W |
| #135 | NVIDIA GeForce GTX 1650 SUPER | Type Desktop |
Performance34. 08 |
ArchitectureTuring | Year of manufacture2019 | Price now250 USD | TDP125 W |
| #136 | NVIDIA GeForce GTX 980 Mobile | Type for Notebooks | Performance33.98 | ArchitectureMaxwell | Year of manufacture2014 | Price now251 USD | TDP100 W |
| #137 | NVIDIA Quadro P4200 | Mobile workstation type | Performance33.57 | ArchitecturePascal | Year of issue2018 | Price now1526 USD | TDP115 W |
| #138 | NVIDIA RTX A1000 Laptop GPU | Notebook Type | Performance33.19 | ArchitectureAmpere | Year of manufacture2022 | Price now − | TDP95 W |
| #139 | NVIDIA Quadro P5200 Max-Q | Workstation type |
Capacity33. 18 |
ArchitecturePascal | Year of manufacture2018 | Price now − | TDP100 W |
| #140 | NVIDIA GeForce RTX 2060 Max-Q | Notebook Type | Capacity33.04 | ArchitectureTuring | Year of manufacture2019 | Price now1680 USD | TDP65 W |
| #141 | NVIDIA Quadro RTX 3000 Mobile | Type Mobile Workstation | Capacity33.02 | ArchitectureTuring | Year of manufacture2019 | Price now2393 USD | TDP80 W |
| #142 | NVIDIA GeForce GTX 970 | Type Desktop | Productivity32.75 | ArchitectureMaxwell | Year of manufacture2014 | Price now160 USD | TDP150 W |
| #143 | AMD Radeon RX 590 | Type Desktop |
Capacity32. 72 |
ArchitecturePolaris | Year of manufacture2018 | Price now141 USD | TDP175 W |
| #144 | NVIDIA GeForce GTX 970M SLI | Type for Notebooks | Performance32.69 | ArchitectureMaxwell | Year of manufacture2014 | Price now1326 USD | TDP162 W |
| #145 | NVIDIA GeForce GTX 1060 3 GB | Type desktop | Capacity32.48 | ArchitecturePascal | Year of release2016 | Price now168 USD | TDP120 W |
| #146 | AMD Radeon R9 Fury | Type Desktop | Capacity32.40 | ArchitectureGCN 1.2 | Year of manufacture2015 | Price now107 USD | TDP275 W |
| #147 | AMD Radeon R9 390X | Type Desktop |
Capacity32. 06 |
ArchitectureGCN | Year of manufacture2015 | Price now381 USD | TDP275 W |
| #148 | NVIDIA Quadro P2200 | Workstation type | Performance32.03 | ArchitecturePascal | Year of manufacture2019 | Price now1239 USD | TDP75W |
| #149 | NVIDIA GeForce GTX 780 Ti | Type Desktop | Capacity31.62 | ArchitectureKepler | Year of manufacture2013 | Price now411 USD | TDP250 W |
| #150 | NVIDIA Quadro P4000 (mobile) | Type for mobile workstations | Productivity31.58 | ArchitecturePascal | Year of manufacture2017 | Price now1053 USD | TDP73.4 W |
| #151 | NVIDIA GeForce GTX 1060 Max-Q 6 GB | Notebook Type |
Capacity31. 54 |
ArchitecturePascal | Year of manufacture2017 | Price now1010 USD | TDP60 W |
| #152 | NVIDIA Quadro M5000 | Workstation Type | Capacity31.47 | ArchitectureMaxwell 2.0 | Year of manufacture2015 | Price now797 USD | TDP150 W |
| #153 | AMD Radeon RX 6500 XT | Type Desktop | Capacity31.40 | ArchitectureNavi / RDNA2 | Year of manufacture2022 | Price now184 USD | TDP107 W |
| #154 | AMD Radeon Pro W5500 | Workstation Type | Capacity31.38 | ArchitectureRDNA 1.0 | Year of manufacture2020 | Price now535 USD | TDP125 W |
| #155 | NVIDIA GeForce GTX TITAN Z | Type desktop |
Capacity31. 12 |
ArchitectureKepler | Year of manufacture2014 | Price now1081 USD | TDP375 W |
| #156 | AMD Radeon RX 5500 XT | Type Desktop | Capacity31.11 | ArchitectureRDNA 1.0 | Year of manufacture2019 | Price now506 USD | TDP130 W |
| #157 | AMD Radeon Pro 5600M | Mobile workstation type | Productivity31.00 | ArchitectureNavi / RDNA | Year of manufacture2020 | Price now − | TDP50 W |
| #158 | NVIDIA GeForce GTX TITAN BLACK | Type Desktop | Productivity30.95 | ArchitectureKepler | Year of manufacture2014 | Price now477 USD | TDP250 W |
| #159 | NVIDIA GeForce RTX 3050 Mobile | Notebook Type |
Capacity30. 90 |
ArchitectureAmpere | Year of manufacture2021 | Price now − | TDP60 W |
| #160 | NVIDIA GeForce GTX 1060 5 GB | Type desktop | Capacity30.77 | ArchitecturePascal | Year of manufacture2017 | Price now203 USD | TDP120 W |
| #161 | AMD Radeon R9 390 | Type Desktop | Performance30.64 | ArchitectureGCN 2.0 | Year of issue2015 | Price now350 USD | TDP300 W |
| #162 | AMD Radeon RX 580 | Type Desktop | Capacity30.22 | ArchitecturePolaris | Year of manufacture2017 | Price now226 USD | TDP185 W |
| #163 | NVIDIA Quadro P4000 Max-Q | Mobile workstation type |
Performance29. 86 |
ArchitecturePascal | Year of manufacture2017 | Price now803 USD | TDP80 W |
| #164 | NVIDIA GeForce GTX 1660 Ti Max-Q | Notebook Type | Performance29.86 | ArchitectureTuring | Year of manufacture2019 | Price now1037 USD | TDP60 W |
| #165 | AMD Radeon RX 5500 | Type desktop | Performance29.85 | ArchitectureRDNA 1.0 | Year of manufacture2019 | Price now551 USD | TDP110 W |
| #166 | NVIDIA Quadro P3200 | Mobile workstation type | Productivity29.74 | ArchitecturePascal | Year of manufacture2017 | Price now2122 USD | TDP78 W |
| #167 | AMD Radeon RX 480 | Type Desktop |
Performance29. 41 |
ArchitecturePolaris | Year of manufacture2016 | Price now156 USD | TDP150 W |
| #168 | NVIDIA Quadro P3200 Max-Q | Type for mobile workstations | Capacity29.32 | ArchitecturePascal | Year of manufacture2018 | Price now − | TDP75 W |
| #169 | AMD Radeon RX 580 (Mobile) | Notebook Type | Capacity29.20 | ArchitecturePolaris | Year of manufacture2017 | Price now410 USD | TDP100 W |
| #170 | AMD Radeon R9 295X2 | Type Desktop | Capacity29.20 | ArchitectureGCN 2.0 | Year of manufacture2014 | Price now600 USD | TDP500 W |
| #171 | AMD Radeon R9 Nano | Type desktop |
Performance28. 75 |
ArchitectureGCN 1.2 | Year of manufacture2015 | Price now372 USD | TDP175 W |
| #172 | NVIDIA Quadro P3000 (mobile) | Type for mobile workstations | Performance28.33 | ArchitecturePascal | Year of manufacture2017 | Price now537 USD | TDP75 W |
| #173 | NVIDIA Quadro T1000 (mobile) | Type for mobile workstations | Productivity28.30 | ArchitectureTuring | Year of manufacture2019 | Price now1890 USD | TDP50 W |
| #174 | AMD Radeon Pro Duo | Workstation Type | Capacity28.19 | ArchitectureGCN 3.0 | Year of manufacture2016 | Price now3051 USD | TDP350 W |
| #175 | AMD Radeon Pro 5500 XT | Workstation type |
Performance28. 11 |
ArchitectureRDNA 1.0 | Year of manufacture2020 | Price now2499 USD | TDP125 W |
| #176 | NVIDIA GeForce GTX TITAN | Type Desktop | Performance27.64 | ArchitectureKepler | Year of manufacture2013 | Price now406 USD | TDP250 W |
| #177 | NVIDIA GeForce GTX 1060 Mobile | Notebook Type | Productivity27.64 | ArchitecturePascal | Year of manufacture2016 | Price now240 USD | TDP80 W |
| #178 | NVIDIA Quadro K6000 | Workstation type | Performance27.48 | ArchitectureKepler | Year of manufacture2013 | Price now816 USD | TDP225 W |
| #179 | AMD Radeon R9 290 | Type Desktop |
Capacity27. 41 |
ArchitectureGCN 2.0 | Year of manufacture2013 | Price now187 USD | TDP275 W |
| #180 | AMD Radeon HD 8970M Crossfire | Notebook Type | Performance27.31 | ArchitectureGCN | Year of issue2012 | Price now170 USD | TDP200 W |
| #181 | NVIDIA GeForce GTX 780 | Type Desktop | Performance27.27 | ArchitectureKepler | Year of manufacture2013 | Price now11 USD | TDP250 W |
| #182 | AMD Radeon RX 470 | Type desktop | Productivity27.11 | ArchitecturePolaris | Year of manufacture2016 | Price now15 USD | TDP120 W |
| #183 | AMD Radeon Pro WX 7100 | Workstation Type |
Capacity26. 85 |
ArchitecturePolaris | Year of manufacture2017 | Price now582 USD | TDP130W |
| #184 | NVIDIA Quadro M5500 | Type for mobile workstations | Capacity26.81 | ArchitectureMaxwell | Year of manufacture2016 | Price now1700 USD | TDP150 W |
| #185 | AMD Radeon RX 580 2048SP | Type desktop | Performance26.60 | ArchitectureGCN 4.0 | Year of manufacture2018 | Price now1373 USD | TDP150 W |
| #186 | NVIDIA GeForce GTX 1650 | Type Desktop | Performance26.47 | ArchitectureTuring | Year of manufacture2019 | Price now279 USD | TDP75 W |
| #187 | AMD Radeon RX 580X | Type desktop |
Capacity26. 42 |
ArchitectureGCN 4.0 | Year of manufacture2018 | Price now191 USD | TDP185 W |
| #188 | NVIDIA GeForce GTX 1650 Ti Mobile | Notebook Type | Capacity26.41 | ArchitectureTuring | Year of release2020 | Price now892 USD | TDP50 W |
| #189 | NVIDIA T1000 8 GB | Type Desktop | Performance26.38 | ArchitectureTuring | Year of manufacture2021 | Price now1500 USD | TDP50 W |
| #190 | NVIDIA Tesla M60 | Workstation Type | Capacity26.32 | ArchitectureMaxwell 2.0 | Year of manufacture2015 | Price now167 USD | TDP300 W |
| #191 | NVIDIA GeForce RTX 2050 Mobile | Notebook Type |
Capacity26. 29 |
ArchitectureAmpere | Year of manufacture2021 | Price now − | TDP30W |
| #192 | NVIDIA T1000 | Type Desktop | Performance26.27 | ArchitectureTuring | Year of manufacture2021 | Price now164 USD | TDP50 W |
| #193 | AMD Radeon Pro 580 | Workstation type | Performance26.26 | ArchitectureGCN 4.0 | Year of manufacture2017 | Price now5999 USD | TDP150 W |
| #194 | AMD FirePro W9100 | Workstation type | Capacity26.15 | ArchitectureGCN 2.0 | Year of manufacture2014 | Price now1542 USD | TDP275 W |
| #195 | AMD Radeon Pro 580X | Type for workstations |
Performance25. 54 |
ArchitectureGCN 4.0 | Year of manufacture2019 | Price now5999 USD | TDP150 W |
| #196 | AMD Radeon RX 5600M | Notebook type | Performance25.53 | ArchitectureNavi / RDNA | Year of manufacture2020 | Price now525 USD | TDP60 W |
| #197 | NVIDIA Tesla M6 | Workstation type | Performance25.44 | ArchitectureMaxwell 2.0 | Year of manufacture2015 | Price now350 USD | TDP100 W |
| #198 | NVIDIA GeForce GTX 1650 Ti | Type Desktop | Performance25.39 | ArchitectureTuring | Year of manufacture − | Price now1297 USD | TDP75 W |
| #199 | AMD Radeon Pro 5300 | Workstation type |
Performance25. 38 |
ArchitectureRDNA 1.0 | Year of manufacture2020 | Price now3649 USD | TDP85W |
| #200 | NVIDIA GeForce GTX 880M SLI | Notebook type | Performance25.23 | ArchitectureKepler | Year of manufacture2014 | Price now3098 USD | TDP206 W |
| №1 | AMD Radeon VII | Type desktop | Rating100.00 | Performance56.99 | Year of manufacture2019 | Price now218 USD | TDP295 W |
| #2 | NVIDIA GeForce GTX 1080 Mobile | Notebook Type | Rating100.00 | Performance47.96 | Year of manufacture2016 | Price now230 USD | TDP150 W |
| #3 | NVIDIA Tesla M40 | Workstation type |
Rating95. 75 |
Performance34.27 | Year of manufacture2015 | Price now151 USD | TDP250 W |
| #4 | NVIDIA GeForce GTX 1070 SLI (Mobile) | Notebook Type | Rating95.62 | Performance54.63 | Year of manufacture2016 | Price now274 USD | TDP− |
| #5 | NVIDIA TITAN Xp | Type Desktop | Rating93.90 | Productivity65.92 | Year of manufacture2017 | Price now216 USD | TDP250 W |
| #6 | NVIDIA Tesla P40 | Workstation Type | Rating92.11 | Performance57.13 | Year of manufacture2016 | Price now12 USD | TDP250 W |
| #7 | AMD Radeon RX 590 | Type desktop |
Rating77. 90 |
Productivity32.72 | Year of issue2018 | Price now141 USD | TDP175 W |
| #8 | NVIDIA GeForce RTX 2060 Super | Type Desktop | Rating77.52 | Productivity56.00 | Year of manufacture2019 | Price now288 USD | TDP175 W |
| #9 | AMD Radeon RX 470 | Type Desktop | Rating74.24 | Productivity27.11 | Year of manufacture2016 | Price now15 USD | TDP120 W |
| #10 | NVIDIA GeForce GTX 1660 Super | Type Desktop | Rating72.92 | Performance43.21 | Year of manufacture2019 | Price now241 USD | TDP125 W |
| #11 | NVIDIA GeForce GTX 1070 SLI | Type Desktop |
Rating69. 09 |
Performance58.36 | Year of manufacture2016 | Price now238 USD | TDP300 W |
| #12 | AMD Radeon RX 6500 XT | Type Desktop | Rating62.05 | Productivity31.40 | Year of manufacture2022 | Price now184 USD | TDP107 W |
| #13 | AMD Radeon R9 Fury | Type Desktop | Rating59.08 | Productivity32.40 | Year of manufacture2015 | Price now107 USD | TDP275 W |
| #14 | AMD Radeon Pro 570 | Type for workstations | Rating57.11 | Productivity21.46 | Year of manufacture2017 | Price now157 USD | TDP120 W |
| #15 | NVIDIA GeForce GTX 1070 Ti | Type desktop |
Rating55. 87 |
Performance49.44 | Year of release2017 | Price now293 USD | TDP180 W |
| #16 | NVIDIA T1000 | Type Desktop | Rating53.96 | Performance26.27 | Year of manufacture2021 | Price now164 USD | TDP50 W |
| #17 | NVIDIA Tesla K80 | Workstation Type | Rating52.06 | Productivity23.79 | Year of manufacture2014 | Price now111 USD | TDP300 W |
| #18 | NVIDIA Tesla M60 | Workstation Type | Rating51.78 | Productivity26.32 | Year of manufacture2015 | Price now167 USD | TDP300W |
| #19 | NVIDIA GeForce GTX 1650 SUPER | Type Desktop |
Rating51. 49 |
Productivity34.08 | Year of manufacture2019 | Price now250 USD | TDP125 W |
| #20 | AMD Radeon Pro W6400 | Workstation type | Rating48.55 | Performance20.92 | Year of manufacture2022 | Price now256 USD | TDP50 W |
| #21 | NVIDIA GeForce GTX 1060 3 GB | Type Desktop | Rating47.03 | Productivity32.48 | Year of manufacture2016 | Price now168 USD | TDP120 W |
| #22 | AMD Radeon RX 6400 | Type desktop | Rating45.38 | Productivity23.51 | Year of manufacture2022 | Price now167 USD | TDP53 W |
| #23 | NVIDIA GeForce GTX 1060 5 GB | Type Desktop |
Rating43. 90 |
Productivity30.77 | Year of release2017 | Price now203 USD | TDP120 W |
| #24 | NVIDIA GeForce GTX 1060 Mobile | Notebook Type | Rating42.81 | Productivity27.64 | Year of manufacture2016 | Price now240 USD | TDP80 W |
| #25 | AMD Radeon RX 480 | Type desktop | Rating41.84 | Productivity29.41 | Year of manufacture2016 | Price now156 USD | TDP150 W |
| #26 | NVIDIA GeForce GTX 980 Mobile | Notebook Type | Rating39.98 | Performance33.98 | Year of manufacture2014 | Price now251 USD | TDP100 W |
| #27 | NVIDIA GeForce GTX 965M SLI | Notebook Type |
Rating38. 72 |
Productivity24.68 | Year of manufacture2015 | Price now149 USD | TDP− |
| #28 | AMD Radeon RX 580X | Type Desktop | Rating38.60 | Productivity26.42 | Year of manufacture2018 | Price now191 USD | TDP185 W |
| #29 | AMD Radeon HD 8970M Crossfire | Notebook Type | Rating37.75 | Productivity27.31 | Year of manufacture2012 | Price now170 USD | TDP200 W |
| #30 | NVIDIA T600 | Type Desktop | Rating37.03 | Productivity22.17 | Year of manufacture2021 | Price now190 USD | TDP40 W |
| #31 | AMD Radeon RX 470 (Mobile) | Notebook Type |
Rating36. 86 |
Productivity18.74 | Year of manufacture2016 | Price now148 USD | TDP120 W |
| #32 | NVIDIA Quadro P620 | Workstation type | Rating34.77 | Performance12.29 | Year of manufacture2019 | Price now170 USD | TDP25 W |
| #33 | AMD Radeon RX 580 | Type desktop | Rating34.59 | Performance30.22 | Year of manufacture2017 | Price now226 USD | TDP185 W |
| #34 | NVIDIA GeForce GTX 970 | Type Desktop | Rating34.15 | Productivity32.75 | Year of manufacture2014 | Price now160 USD | TDP150 W |
| #35 | AMD Radeon Pro 560X | Mobile Workstation Type |
Rating30. 86 |
Performance12.46 | Year of manufacture2017 | Price now133 USD | TDP35 W |
| #36 | AMD Radeon HD 7970M Crossfire | Notebook Type | Rating30.80 | Performance21.29 | Year of manufacture2012 | Price now126 USD | TDP200 W |
| #37 | NVIDIA GeForce GTX 1650 | Type Desktop | Rating30.48 | Productivity26.47 | Year of manufacture2019 | Price now279 USD | TDP75 W |
| #38 | AMD Radeon Pro 460 | Mobile workstation type | Rating30.15 | Performance11.69 | Year of manufacture2016 | Price now100 USD | TDP35 W |
| #39 | AMD Radeon Pro 560 | Mobile workstation type |
Rating29. 90 |
Performance11.77 | Year of manufacture2017 | Price now127 USD | TDP35 W |
| #40 | NVIDIA GeForce GTX 780M SLI | Notebook Type | Rating29.73 | Productivity22.73 | Year of manufacture2013 | Price now149 USD | TDP200W |
| #41 | NVIDIA GeForce GTX 680M SLI | Notebook type | Rating27.45 | Performance21.85 | Year of manufacture2012 | Price now149 USD | TDP− |
| #42 | NVIDIA GeForce GTX 1630 | Type Desktop | Rating25.21 | Productivity15.81 | Year of manufacture2022 | Price now177 USD | TDP75 W |
| #43 | NVIDIA GeForce GTX 780 | Type Desktop |
Rating23. 94 |
Performance27.27 | Year of manufacture2013 | Price now11 USD | TDP250 W |
| #44 | AMD Radeon R9 285 | Type desktop | Rating21.99 | Productivity22.63 | Year of manufacture2014 | Price now73 USD | TDP190 W |
| #45 | NVIDIA GeForce GTX 950 | Type Desktop | Rating21.55 | Performance18.22 | Year of manufacture2015 | Price now58 USD | TDP90 W |
| #46 | AMD Radeon R9 290 | Type Desktop | Rating20.31 | Productivity27.41 | Year of manufacture2013 | Price now187 USD | TDP275 W |
| #47 | AMD Radeon R9 290X | Type Desktop |
Rating19. 12 |
Productivity25.15 | Year of manufacture2013 | Price now167 USD | TDP350 W |
| #48 | NVIDIA Quadro P600 | Workstation type | Rating18.64 | Performance11.03 | Year of manufacture2017 | Price now207 USD | TDP25 W |
| #49 | NVIDIA GeForce GTX 680 | Type Desktop | Rating18.59 | Performance18.84 | Year of manufacture2012 | Price now99 USD | TDP195 W |
| #50 | NVIDIA GeForce GTX 760 | Type Desktop | Rating18.38 | Performance16.16 | Year of manufacture2013 | Price now49 USD | TDP170 W |
| #51 | AMD Radeon R9 380 | Type Desktop |
Rating17. 76 |
Performance21.17 | Year of manufacture2015 | Price now165 USD | TDP220 W |
| #52 | NVIDIA GeForce GTX 670M | Type for laptops | Rating17.64 | Performance6.02 | Year of manufacture2012 | Price now3 USD | TDP75 W |
| #53 | AMD Radeon RX 550X (Mobile) | Notebook Type | Rating17.59 | Performance12.88 | Year of manufacture2019 | Price now299 USD | TDP50 W |
| #54 | NVIDIA P104-100 | Type Desktop | Rating17.07 | Productivity15.07 | Year of manufacture2017 | Price now19 USD | TDP− |
| #55 | NVIDIA GeForce GTX 770 | Type Desktop |
Rating17. 03 |
Performance19.92 | Year of manufacture2013 | Price now117 USD | TDP230 W |
| #56 | NVIDIA GeForce GTX 1050 Mobile | Notebook Type | Rating17.00 | Performance15.11 | Year of manufacture2017 | Price now256 USD | TDP75 W |
| #57 | NVIDIA T400 4 GB | Type desktop | Rating16.53 | Performance12.25 | Year of manufacture2021 | Price now198 USD | TDP30 W |
| #58 | AMD Radeon RX 550 (Mobile) | Notebook Type | Rating15.42 | Productivity15.02 | Year of manufacture2017 | Price now294 USD | TDP50 W |
| #59 | AMD Radeon RX 540 | Notebook type |
Rating14. 39 |
Productivity9.44 | Year of manufacture2017 | Price now166 USD | TDP75 W |
| #60 | AMD Radeon RX Vega 5 | Type for laptops | Rating13.95 | Productivity9.43 | Year of manufacture2020 | Price now287 USD | TDP15 W |
| #61 | AMD Radeon Pro 450 | Mobile workstation type | Rating12.63 | Performance9.22 | Year of release2016 | Price now183 USD | TDP75 W |
| #62 | AMD Radeon HD 6990M Crossfire | Notebook Type | Rating12.37 | Productivity15.74 | Year of manufacture2011 | Price now170 USD | TDP− |
| #63 | NVIDIA GeForce GTX 485M SLI | Notebook Type |
Rating12. 12 |
Productivity14.60 | Year of manufacture2011 | Price now149 USD | TDP100 W |
| #64 | NVIDIA GeForce GT 1030 | Type Desktop | Rating11.61 | Performance8.57 | Year of manufacture2017 | Price now111 USD | TDP30 W |
| #65 | AMD Radeon RX 640 | Notebook type | Rating11.49 | Performance5.74 | Year of manufacture2019 | Price now193 USD | TDP50 W |
| #66 | NVIDIA P106-100 | Type desktop | Rating11.27 | Productivity12.88 | Year of manufacture2017 | Price now13 USD | TDP120 W |
| #67 | NVIDIA Quadro K4200 | Workstation Type |
Rating11. 04 |
Performance14.67 | Year of manufacture2014 | Price now185 USD | TDP108 W |
| #68 | AMD Radeon R9 280X | Type desktop | Rating10.90 | Performance19.77 | Year of manufacture2013 | Price now180 USD | TDP200 W |
| #69 | AMD Radeon HD 8970M | Notebook Type | Rating10.78 | Performance13.13 | Year of manufacture2013 | Price now135 USD | TDP100 W |
| #70 | NVIDIA GeForce GTX 570 | Type Desktop | Rating10.61 | Performance13.23 | Year of manufacture2010 | Price now13 USD | TDP219 W |
| #71 | AMD Radeon PRO WX 3100 | Type Mobile Workstation |
Rating10. 24 |
Performance8.90 | Year of manufacture2017 | Price now242 USD | TDP65 W |
| #72 | AMD Radeon Sky 500 | Type Desktop | Rating9.96 | Performance16.04 | Year of manufacture2013 | Price now129 USD | TDP150 W |
| #73 | NVIDIA GeForce GTX 765M SLI | Notebook Type | Rating9.85 | Performance13.19 | Year of manufacture2013 | Price now149 USD | TDP130 W |
| #74 | AMD Radeon R9 370 | Type Desktop | Rating9.69 | Productivity16.00 | Year of manufacture2015 | Price now175 USD | TDP110 W |
| #75 | NVIDIA Quadro M600M | Mobile workstation type |
Rating9. 49 |
Productivity6.80 | Year of manufacture2015 | Price now103 USD | TDP30 W |
| #76 | NVIDIA GeForce GTX 960 | Type Desktop | Rating9.48 | Performance20.43 | Year of manufacture2015 | Price now253 USD | TDP100 W |
| #77 | NVIDIA GeForce GTX 770M SLI | Notebook Type | Rating9.46 | Performance12.93 | Year of manufacture2013 | Price now149 USD | TDP150 W |
| #78 | AMD Radeon HD 6970M Crossfire | Notebook Type | Rating9.44 | Performance13.78 | Year of manufacture2011 | Price now170 USD | TDP− |
| #79 | AMD Radeon R7 360 | Type desktop |
Rating9. 25 |
Performance10.31 | Year of manufacture2015 | Price now14 USD | TDP80 W |
| #80 | NVIDIA GeForce GTX 680MX | Notebook Type | Rating8.85 | Performance14.46 | Year of manufacture2012 | Price now200 USD | TDP122 W |
| #81 | NVIDIA Quadro K1200 | Workstation type | Rating8.75 | Productivity9.75 | Year of manufacture2015 | Price now134 USD | TDP45 W |
| #82 | AMD Radeon RX Vega 6 (Ryzen 2000) | Notebook Type | Rating8.75 | Performance7.46 | Year of manufacture2018 | Price now248 USD | TDP− |
| #83 | AMD Radeon HD 7870 XT | Type Desktop |
Rating8. 59 |
Performance15.14 | Year of manufacture2012 | Price now133 USD | TDP185 W |
| #84 | AMD Radeon RX 550 | Type desktop | Rating8.47 | Performance9.17 | Year of manufacture2017 | Price now163 USD | TDP50 W |
| #85 | NVIDIA GeForce GTX 580 | Type Desktop | Rating8.17 | Productivity15.30 | Year of manufacture2010 | Price now11 USD | TDP244 W |
| #86 | NVIDIA GeForce GTX 470 | Type Desktop | Rating8.13 | Performance10.53 | Year of manufacture2010 | Price now10 USD | TDP225 W |
| #87 | NVIDIA GeForce GTX 580M SLI | Type for Notebooks |
Rating7. 87 |
Productivity15.20 | Year of manufacture2011 | Price now249 USD | TDP100 W |
| #88 | NVIDIA GRID K520 | Workstation type | Rating7.79 | Performance11.51 | Year of issue2013 | Price now160 USD | TDP225 W |
| #89 | AMD Radeon R9 280 | Type Desktop | Rating7.77 | Performance19.20 | Year of manufacture2014 | Price now238 USD | TDP200 W |
| #90 | AMD FirePro W4300 | Workstation type | Rating7.72 | Productivity9.80 | Year of manufacture2015 | Price now236 USD | TDP50 W |
| #91 | AMD Radeon R9 380X | Type Desktop |
Rating7. 70 |
Productivity21.13 | Year of manufacture2015 | Price now22 USD | TDP250 W |
| #92 | NVIDIA GeForce GTX 760 Ti OEM | Type Desktop | Rating7.39 | Performance18.38 | Year of manufacture2013 | Price now229 USD | TDP170 W |
| #93 | AMD FirePro S7000 | Workstation type | Rating7.34 | Performance14.11 | Year of manufacture2012 | Price now257 USD | TDP150 W |
| #94 | AMD FirePro W7000 | Workstation Type | Rating7.23 | Productivity14.60 | Year of manufacture2012 | Price now280 USD | TDP150 W |
| #95 | NVIDIA GeForce GTX 560 | Type desktop |
Rating6. 76 |
Performance9.17 | Year of manufacture2011 | Price now16 USD | TDP150 W |
| #96 | AMD Radeon 550 | Type Desktop | Rating6.75 | Performance6.63 | Year of manufacture2017 | Price now135 USD | TDP50 W |
| #97 | NVIDIA Quadro P400 | Workstation Type | Rating6.67 | Performance5.40 | Year of manufacture2017 | Price now87 USD | TDP30 W |
| #98 | AMD Radeon RX 550X | Type Desktop | Rating6.55 | Productivity8.00 | Year of manufacture2018 | Price now259 USD | TDP50 W |
| #99 | AMD Radeon RX 570X | Type Desktop |
Rating6. 18 |
Performance6.51 | Year of manufacture2018 | Price now186 USD | TDP120 W |
| #100 | NVIDIA Quadro K2200M | Type for workstations | Rating6.04 | Productivity12.09 | Year of manufacture2014 | Price now228 USD | TDP65 W |
| #101 | NVIDIA GeForce GTX 660 Ti | Type Desktop | Rating5.94 | Performance14.81 | Year of manufacture2012 | Price now184 USD | TDP150 W |
| #102 | NVIDIA GeForce GTX 470M SLI | Notebook Type | Rating5.82 | Performance10.19 | Year of manufacture2010 | Price now149 USD | TDP− |
| #103 | NVIDIA GeForce GTX 560M SLI | Type for laptops |
Rating5. 80 |
Performance10.18 | Year of manufacture2011 | Price now149 USD | TDP100 W |
| #104 | NVIDIA GeForce GTX 480M SLI | Notebook Type | Rating5.78 | Performance10.16 | Year of manufacture2010 | Price now149 USD | TDP100 W |
| #105 | AMD Radeon HD 7970 | Type Desktop | Rating5.76 | Performance17.78 | Year of manufacture2011 | Price now275 USD | TDP250 W |
| #106 | NVIDIA GeForce GTX 660 | Type Desktop | Rating5.75 | Productivity13.53 | Year of manufacture2012 | Price now158 USD | TDP140 W |
| #107 | AMD Radeon RX Vega 8 | Notebook Type |
Rating5. 67 |
Performance5.88 | Year of manufacture2017 | Price now273 USD | TDP65W |
| #108 | AMD FirePro W5000 | Workstation type | Rating5.66 | Performance10.12 | Year of manufacture2012 | Price now169 USD | TDP75 W |
| #109 | NVIDIA GeForce GTX 285M SLI | Notebook Type | Rating5.53 | Performance9.94 | Year of manufacture2009 | Price now149 USD | TDP150 W |
| #110 | AMD Radeon R7 370 | Type Desktop | Rating5.34 | Performance15.22 | Year of manufacture2015 | Price now14 USD | TDP100 W |
| #111 | AMD Radeon R9 270 | Type desktop |
Rating4. 97 |
Performance14.59 | Year of manufacture2013 | Price now213 USD | TDP150 W |
| #112 | NVIDIA Quadro P500 | Mobile workstation type | Rating4.95 | Performance5.09 | Year of release2017 | Price now300 USD | TDP18 W |
| #113 | AMD Radeon R7 260X | Type Desktop | Rating4.79 | Performance10.65 | Year of manufacture2013 | Price now89 USD | TDP115 W |
| #114 | NVIDIA Tesla C2070 | Workstation type | Rating4.62 | Productivity10.50 | Year of manufacture2011 | Price now17 USD | TDP238 W |
| #115 | AMD FirePro M5100 | Mobile workstation type |
Rating4. 42 |
Performance7.12 | Year of manufacture2013 | Price now105 USD | TDP− |
| #116 | AMD Radeon HD 7870 | Type Desktop | Rating4.20 | Performance15.81 | Year of manufacture2012 | Price now297 USD | TDP200 W |
| #117 | NVIDIA GeForce GTX 770M | Notebook Type | Rating4.18 | Productivity9.46 | Year of manufacture2013 | Price now178 USD | TDP50 W |
| #118 | NVIDIA GeForce GTX 460M SLI | Notebook Type | Rating4.05 | Performance8.54 | Year of manufacture2010 | Price now149 USD | TDP− |
| #119 | AMD Radeon R7 260 | Type Desktop |
Rating4. 03 |
Productivity9.79 | Year of manufacture2013 | Price now89 USD | TDP95 W |
| #120 | AMD FirePro W4100 | Workstation type | Rating3.98 | Performance5.19 | Year of issue2015 | Price now167 USD | TDP50 W |
| #121 | NVIDIA GRID K2 | Workstation type | Rating3.92 | Performance9.27 | Year of manufacture2013 | Price now204 USD | TDP225 W |
| #122 | AMD Radeon 550X | Type desktop | Rating3.87 | Performance4.84 | Year of manufacture2019 | Price now259 USD | TDP50 W |
| #123 | NVIDIA GeForce GTX 280M SLI | Notebook Type |
Rating3. 86 |
Performance8.35 | Year of manufacture2009 | Price now149 USD | TDP150W |
| #124 | NVIDIA GeForce GTX 850M | Notebook type | Rating3.83 | Performance8.69 | Year of manufacture2014 | Price now163 USD | TDP45 W |
| #125 | ATI Mobility Radeon HD 5870 | Notebook Type | Rating3.79 | Performance7.08 | Year of manufacture2010 | Price now108 USD | TDP50 W |
| #126 | AMD Radeon RX Vega 6 | Notebook Type | Rating3.79 | Performance3.97 | Year of manufacture2018 | Price now273 USD | TDP− |
| #127 | NVIDIA GeForce 945M | Type for laptops |
Rating3. 74 |
Productivity6.80 | Year of manufacture2015 | Price now163 USD | TDP75 W |
| #128 | AMD Radeon 520 | Notebook Type | Rating3.69 | Performance2.67 | Year of manufacture2017 | Price now140 USD | TDP50 W |
| #129 | AMD FirePro V7900 | Workstation type | Rating3.59 | Productivity7.80 | Year of manufacture2011 | Price now156 USD | TDP150 W |
| #130 | NVIDIA GeForce GTX 260M SLI | Notebook Type | Rating3.47 | Performance7.93 | Year of manufacture2009 | Price now149 USD | TDP150 W |
| #131 | NVIDIA GeForce GTX 465 | Type Desktop |
Rating3. 46 |
Performance9.08 | Year of manufacture2010 | Price now52 USD | TDP200 W |
| #132 | AMD Radeon HD 6990M | Notebook type | Rating3.43 | Performance8.87 | Year of manufacture2011 | Price now190 USD | TDP100 W |
| #133 | NVIDIA GeForce 9800 GX2 | Type Desktop | Rating3.38 | Performance2.70 | Year of manufacture2008 | Price now6 USD | TDP197 W |
| #134 | AMD FirePro M6100 | Mobile workstation type | Rating3.30 | Productivity6.60 | Year of manufacture2013 | Price now120 USD | TDP− |
| #135 | NVIDIA GeForce GTX 680M | Type for laptops |
Rating3. 25 |
Performance10.67 | Year of manufacture2012 | Price now293 USD | TDP100 W |
| #136 | NVIDIA GeForce GTX 485M | Notebook Type | Rating3.22 | Performance7.99 | Year of manufacture2010 | Price now163 USD | TDP100 W |
| #137 | AMD Radeon HD 7850 | Type Desktop | Rating3.21 | Performance12.97 | Year of manufacture2012 | Price now260 USD | TDP130 W |
| #138 | NVIDIA GeForce GTX 460 | Type Desktop | Rating2.91 | Performance7.77 | Year of manufacture2010 | Price now50 USD | TDP160 W |
| #139 | NVIDIA GeForce 9800M GTX SLI | Notebook Type |
Rating2. 89 |
Performance7.25 | Year of manufacture2008 | Price now149 USD | TDP150W |
| #140 | NVIDIA GeForce GTX 560 Ti | Type Desktop | Rating2.71 | Performance10.28 | Year of manufacture2011 | Price now191 USD | TDP160 W |
| #141 | NVIDIA GeForce GT 520MX | Notebook type | Rating2.68 | Performance0.97 | Year of manufacture2011 | Price now3 USD | TDP20 W |
| #142 | NVIDIA GeForce GTX 650 Ti | Type Desktop | Rating2.58 | Performance8.59 | Year of manufacture2012 | Price now139 USD | TDP110 W |
| #143 | NVIDIA T400 | Type desktop |
Rating2. 45 |
Productivity12.40 | Year of manufacture2021 | Price now55 USD | TDP30 W |
| #144 | NVIDIA Quadro 5010M | Mobile workstation type | Rating2.42 | Productivity6.00 | Year of release2011 | Price now134 USD | TDP100 W |
| #145 | NVIDIA GeForce GTX 480M | Notebook type | Rating2.41 | Performance6.94 | Year of manufacture2010 | Price now163 USD | TDP100 W |
| #146 | NVIDIA GeForce GTX 580M | Notebook Type | Rating2.37 | Performance7.03 | Year of manufacture2011 | Price now170 USD | TDP100 W |
| #147 | AMD FirePro W6150M | Workstation Type |
Rating2. 34 |
Performance5.13 | Year of manufacture2015 | Price now299 USD | TDP− |
| #148 | AMD Radeon HD 6950 | Type Desktop | Rating2.31 | Performance8.93 | Year of manufacture2010 | Price now168 USD | TDP200 W |
| #149 | AMD FirePro W2100 | Workstation type | Rating2.31 | Performance3.06 | Year of manufacture2015 | Price now142 USD | TDP26 W |
| #150 | NVIDIA GeForce GTX 650 Ti Boost | Type Desktop | Rating2.29 | Performance11.21 | Year of manufacture2013 | Price now270 USD | TDP134 W |
| #151 | NVIDIA P106-090 | Type Desktop |
Rating2. 17 |
Performance8.14 | Year of manufacture2017 | Price now24 USD | TDP75 W |
| #152 | AMD FirePro M6000 | Mobile workstation type | Rating2.12 | Performance6.17 | Year of manufacture2012 | Price now162 USD | TDP43 W |
| #153 | NVIDIA GeForce GTX 570M | Notebook Type | Rating2.08 | Performance6.47 | Year of manufacture2011 | Price now163 USD | TDP75 W |
| #154 | AMD Radeon HD 6990 | Type desktop | Rating2.03 | Performance10.21 | Year of manufacture2011 | Price now252 USD | TDP375 W |
| #155 | AMD Radeon HD 6970 | Type Desktop |
Rating2. 02 |
Productivity9.60 | Year of manufacture2010 | Price now223 USD | TDP250 W |
| #156 | NVIDIA GeForce GTX 960A | Type desktop | Rating2.01 | Performance8.16 | Year of manufacture2015 | Price now243 USD | TDP75 W |
| #157 | AMD Radeon HD 6970M | Notebook Type | Rating1.89 | Performance7.69 | Year of manufacture2011 | Price now257 USD | TDP75 W |
| #158 | NVIDIA Quadro K4000M | Mobile workstation type | Rating1.76 | Performance6.81 | Year of manufacture2012 | Price now240 USD | TDP100 W |
| #159 | AMD Radeon HD 6870 | Type Desktop |
Rating1. 75 |
Productivity7.50 | Year of manufacture2010 | Price now155 USD | TDP151 W |
| #160 | AMD Radeon R5 M435 | Type Desktop | Rating1.75 | Productivity2.65 | Year of manufacture2016 | Price now120 USD | TDP− |
| #161 | NVIDIA GeForce 8800M GTX SLI | Notebook type | Rating1.69 | Performance5.60 | Year of manufacture2007 | Price now149 USD | TDP130 W |
| #162 | ATI Mobility Radeon HD 5870 Crossfire | Type for Notebooks | Rating1.60 | Performance11.55 | Year of manufacture2010 | Price now56 USD | TDP120 W |
| #163 | ATI Radeon HD 5850 | Type Desktop |
Rating1. 60 |
Performance6.73 | Year of manufacture2009 | Price now135 USD | TDP151 W |
| #164 | NVIDIA GeForce GTX 760M | Notebook Type | Rating1.58 | Performance5.66 | Year of manufacture2013 | Price now163 USD | TDP45 W |
| #165 | NVIDIA GeForce GTX 675M | Notebook Type | Rating1.56 | Performance6.47 | Year of manufacture2012 | Price now218 USD | TDP100 W |
| #166 | NVIDIA GF117 | Type Desktop | Rating1.55 | Performance1.88 | Year of manufacture − | Price now15 USD | TDP− |
| #167 | NVIDIA Quadro 4000M | Type for mobile workstations |
Rating1. 40 |
Performance4.35 | Year of manufacture2011 | Price now118 USD | TDP100 W |
| #168 | AMD Radeon R7 250X | Type Desktop | Rating1.37 | Performance7.68 | Year of manufacture2014 | Price now207 USD | TDP80 W |
| #169 | ATI Radeon HD 5870 | Type Desktop | Rating1.35 | Performance7.68 | Year of manufacture2009 | Price now211 USD | TDP188 W |
| #170 | NVIDIA GeForce 9800M GTS SLI | Type for laptops | Rating1.33 | Performance5.01 | Year of manufacture2008 | Price now149 USD | TDP150 W |
| #171 | NVIDIA GeForce 930M | Notebook type |
Rating1. 28 |
Performance3.41 | Year of manufacture2015 | Price now160 USD | TDP12 W |
| #172 | ATI Mobility Radeon HD 5850 | Notebook Type | Rating1.27 | Performance4.95 | Year of manufacture2010 | Price now153 USD | TDP39 W |
| #173 | ATI FirePro M7740 | Mobile workstation type | Rating1.22 | Performance5.87 | Year of manufacture2009 | Price now255 USD | TDP60 W |
| #174 | Intel HD Graphics 5600 | Notebook Type | Rating1.22 | Performance2.25 | Year of manufacture2015 | Price now121 USD | TDP15 W |
| #175 | NVIDIA Quadro K3000M | Type for mobile workstations |
Rating1. 20 |
Performance5.46 | Year of manufacture2012 | Price now223 USD | TDP75 W |
| #176 | NVIDIA GeForce 845M | Notebook type | Rating1.19 | Performance4.96 | Year of manufacture2014 | Price now163 USD | TDP33 W |
| #177 | AMD FirePro V5900 | Workstation Type | Rating1.16 | Performance4.26 | Year of manufacture2011 | Price now136 USD | TDP75 W |
| #178 | NVIDIA Quadro K2000D | Type for workstations | Rating1.13 | Performance5.46 | Year of manufacture2013 | Price now236 USD | TDP51 W |
| #179 | NVIDIA GeForce GT 740 | Type Desktop |
Rating1. 08 |
Performance5.23 | Year of release2014 | Price now118 USD | TDP64 W |
| #180 | ATI Radeon HD 4890 | Type Desktop | Rating1.03 | Performance5.15 | Year of manufacture2009 | Price now120 USD | TDP190 W |
| #181 | AMD Radeon RX 460 (Mobile) | Notebook type | Rating1.01 | Performance11.97 | Year of manufacture2016 | Price now95 USD | TDP75 W |
| #182 | ATI FirePro V5800 | Workstation Type | Rating1.00 | Performance4.79 | Year of manufacture2010 | Price now203 USD | TDP74W |
| #183 | NVIDIA GeForce 910M | Notebook Type |
Rating0. 96 |
Performance1.96 | Year of manufacture2015 | Price now163 USD | TDP15 W |
| #184 | Intel UHD Graphics 600 | Notebook Type | Rating0.95 | Productivity1.13 | Year of manufacture2017 | Price now274 USD | TDP5 W |
| #185 | NVIDIA GeForce GTX 460 v2 | Type Desktop | Rating0.92 | Productivity6.74 | Year of manufacture2011 | Price now235 USD | TDP160 W |
| #186 | NVIDIA Quadro 2000D | Type for workstations | Rating0.92 | Performance3.33 | Year of manufacture2011 | Price now62 USD | TDP62 W |
| #187 | AMD FirePro V4900 | Workstation type |
Rating0. 92 |
Performance3.31 | Year of release2011 | Price now100 USD | TDP75 W |
| #188 | ATI Mobility Radeon HD 4850 | Notebook Type | Rating0.91 | Performance4.66 | Year of manufacture2009 | Price now187 USD | TDP− |
| #189 | ATI Radeon HD 5770 | Type Desktop | Rating0.90 | Performance5.78 | Year of manufacture2009 | Price now175 USD | TDP108 W |
| #190 | NVIDIA Quadro K2100M | Mobile workstation type | Rating0.88 | Performance4.57 | Year of manufacture2013 | Price now208 USD | TDP55 W |
| #191 | AMD Radeon R8 M535DX | Type desktop |
Rating0. 87 |
Performance2.27 | Year of manufacture2017 | Price now299 USD | TDP− |
| #192 | AMD Radeon HD 6850 | Type desktop | Rating0.84 | Performance6.72 | Year of manufacture2010 | Price now257 USD | TDP127 W |
| #193 | AMD Radeon HD 6790 | Type Desktop | Rating0.83 | Performance5.48 | Year of manufacture2011 | Price now169 USD | TDP150 W |
| #194 | ATI Radeon HD 5970 | Type Desktop | Rating0.82 | Productivity7.60 | Year of manufacture2009 | Price now69 USD | TDP294 W |
| #195 | AMD Radeon HD 7750 | Type desktop |
Rating0. 81 |
Performance5.81 | Year of issue2012 | Price now197 USD | TDP55 W |
| #196 | NVIDIA GeForce GTX 285 | Type Desktop | Rating0.79 | Performance5.21 | Year of manufacture2008 | Price now161 USD | TDP204 W |
| #197 | AMD Radeon HD 8550G+HD 8750M Dual Graphics | Type for Notebook | Rating0.79 | Performance3.33 | Year of manufacture2013 | Price now105 USD | TDP− |
| #198 | NVIDIA GeForce 8800 GTX | Type desktop | Rating0.79 | Performance2.02 | Year of manufacture2006 | Price now61 USD | TDP155 W |
| #199 | NVIDIA GeForce GTX 650 | Type Desktop |
Rating0.
|