GeForce GTX 1080 Ti vs GeForce GTX 1070
- Home
- VGA Benchmarks
- GeForce GTX 1080 Ti vs GeForce GTX 1070
-
GeForce GTX 1080 Ti
155%
-
GeForce GTX 1070
100%
Relative performance
Reasons to consider GeForce GTX 1080 Ti |
55% higher gaming performance. |
Supports PhysX |
Supports G-Sync |
Supports ShadowPlay (allows game streaming/recording with minimum performance penalty) |
Supports Direct3D 12 Async Compute |
Based on an outdated architecture (Nvidia Pascal), there may be no performance optimizations for current games and applications |
Reasons to consider GeForce GTX 1070 |
70 watts lower power draw. This might be a strong point if your current power supply is not enough to handle the GeForce GTX 1080 Ti . |
Supports PhysX |
Supports G-Sync |
Supports ShadowPlay (allows game streaming/recording with minimum performance penalty) |
Supports Direct3D 12 Async Compute |
Based on an outdated architecture (Nvidia Pascal), there may be no performance optimizations for current games and applications |
HWBench recommends GeForce GTX 1080 Ti
The GeForce GTX 1080 Ti is the better performing card based on the game benchmark suite used (124 combinations of games and resolutions).
Core Configuration
GeForce GTX 1080 Ti | GeForce GTX 1070 | |||
---|---|---|---|---|
GPU Name | GP102 (GP102-350-K1-A1) | vs | GP104 (GP104-200-A1) | |
Fab Process | 16 nm | vs | 16 nm | |
Die Size | 471 mm² | vs | 314 mm² | |
Transistors | 12,000 million | vs | 7,200 million | |
Shaders | 3584 | vs | 1920 | |
Compute Units | 28 | vs | 15 | |
Core clock | 1480 MHz | vs | 1506 MHz | |
ROPs | 88 | vs | 64 | |
TMUs | 224 | vs | 120 |
Memory Configuration
GeForce GTX 1080 Ti | GeForce GTX 1070 | |||
---|---|---|---|---|
Memory Type | GDDR5X | vs | GDDR5 | |
Bus Width | 352 bit | vs | 256 bit | |
Memory Speed | 1376 MHz 11008 MHz effective |
vs | 2002 MHz 8008 MHz effective |
|
Memory Size | 11264 Mb | vs | 8192 Mb |
Additional details
GeForce GTX 1080 Ti | GeForce GTX 1070 | |||
---|---|---|---|---|
TDP | 220 watts | vs | 150 watts | |
Release Date | UNRELEASED | vs | 10 Jun 2016 |
-
GeForce GTX 1080 Ti
130. 20 GP/s
-
GeForce GTX 1070
96.40 GP/s
GigaPixels — higher is better
-
GeForce GTX 1080 Ti
332.00 GT/s
-
GeForce GTX 1070
180.70 GT/s
GigaTexels — higher is better
-
GeForce GTX 1080 Ti
484.00 GB/s
-
GeForce GTX 1070
256.30 GB/s
GB/s — higher is better
-
GeForce GTX 1080 Ti
10609.00 GFLOPs
-
GeForce GTX 1070
5783.00 GFLOPs
GFLOPs — higher is better
DX11, Max Detail, 2xMSAA 16xAF
-
GeForce GTX 1080 Ti
224
-
GeForce GTX 1070
157
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
66
-
GeForce GTX 1070
43
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
161
-
GeForce GTX 1070
119
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
123
-
GeForce GTX 1070
86
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
91
-
GeForce GTX 1070
60
FPS (higher is better)
Ultra quality TTA DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
134
-
GeForce GTX 1070
87
FPS (higher is better)
Ultra High Quality, TAA, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
160
-
GeForce GTX 1070
104
FPS (higher is better)
Ultra High Quality TAA, Bahrain, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
163
-
GeForce GTX 1070
101
FPS (higher is better)
Windows 10 x64, Ultra quality, DirectX12
-
GeForce GTX 1080 Ti
55
-
GeForce GTX 1070
38
FPS (higher is better)
Very High Quality TAA, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
156
-
GeForce GTX 1070
100
FPS (higher is better)
Highest quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
145
-
GeForce GTX 1070
107
FPS (higher is better)
Ultra quality DirectX12 Windows10 x64
-
GeForce GTX 1080 Ti
119
-
GeForce GTX 1070
86
FPS (higher is better)
Ultra Quality,DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
120
-
GeForce GTX 1070
70
FPS (higher is better)
Ultra, TSSAA 8tx, ASync on, Vsync off, VULKAN, Windows 10 x64
-
GeForce GTX 1080 Ti
200
-
GeForce GTX 1070
179
FPS (higher is better)
Ultra quality,TTA,Melbourne,DirectX11,Windows 10 x64
-
GeForce GTX 1080 Ti
164
-
GeForce GTX 1070
121
FPS (higher is better)
Ultra quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
119
-
GeForce GTX 1070
93
FPS (higher is better)
Ultra High Quality, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
89
-
GeForce GTX 1070
55
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
116
-
GeForce GTX 1070
93
FPS (higher is better)
DX11, Very High Settings
-
GeForce GTX 1080 Ti
118
-
GeForce GTX 1070
94
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
164
-
GeForce GTX 1070
126
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
116
-
GeForce GTX 1070
76
FPS (higher is better)
Very high Quality, DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
105
-
GeForce GTX 1070
75
FPS (higher is better)
DX11, Max Details, 16:1 AF, 2xMSAA
-
GeForce GTX 1080 Ti
170
-
GeForce GTX 1070
152
FPS (higher is better)
Ultra quality,16:1 HQ-AF,DirectX 12, windows 10 x64
-
GeForce GTX 1080 Ti
154
-
GeForce GTX 1070
121
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
148
-
GeForce GTX 1070
103
FPS (higher is better)
Very high quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
108
-
GeForce GTX 1070
77
FPS (higher is better)
Ultra Detail,16:1 AF, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
71
-
GeForce GTX 1070
43
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
46
-
GeForce GTX 1070
32
FPS (higher is better)
Ultra Quality, HR Textures, DirectX11, Windows 10 x64
-
GeForce GTX 1080 Ti
119
-
GeForce GTX 1070
81
FPS (higher is better)
UltraTX Max Quality, Vulkan, Windows 10 x64
-
GeForce GTX 1080 Ti
64
-
GeForce GTX 1070
40
FPS (higher is better)
Max Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
148
-
GeForce GTX 1070
100
FPS (higher is better)
Maximun Quality, DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
186
-
GeForce GTX 1070
117
FPS (higher is better)
Very High Details, Pure Hair On, FXAA/HBAO+ enabled, 16x AF, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
175
-
GeForce GTX 1070
111
FPS (higher is better)
Highest Details, Pure hair, HBAO+, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
115
-
GeForce GTX 1070
74
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
143
-
GeForce GTX 1070
96
FPS (higher is better)
Ultra quality DirectX12 Windows10 x64
-
GeForce GTX 1080 Ti
149
-
GeForce GTX 1070
117
FPS (higher is better)
Ultra Quality, DirectX12, Async Compute ,Windows 10×64
-
GeForce GTX 1080 Ti
168
-
GeForce GTX 1070
103
FPS (higher is better)
DX11,Max Details, 16:1 HQ-AF, +AA
-
GeForce GTX 1080 Ti
140
-
GeForce GTX 1070
83
FPS (higher is better)
DX11, Max Details, 16:1 AF
-
GeForce GTX 1080 Ti
131
-
GeForce GTX 1070
82
FPS (higher is better)
Ultra Quality, Windows 10 x64
-
GeForce GTX 1080 Ti
102
-
GeForce GTX 1070
71
FPS (higher is better)
Main Leben! quality preset- Vulkan Windows 10×64
-
GeForce GTX 1080 Ti
134
-
GeForce GTX 1070
91
FPS (higher is better)
DX11, Max Detail, 2xMSAA 16xAF
-
GeForce GTX 1080 Ti
209
-
GeForce GTX 1070
129
FPS (higher is better)
High Quality Mode, 8 millon samples, 2xMSAA, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
106
-
GeForce GTX 1070
75
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
53
-
GeForce GTX 1070
34
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
131
-
GeForce GTX 1070
87
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
98
-
GeForce GTX 1070
67
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
64
-
GeForce GTX 1070
41
FPS (higher is better)
Ultra quality TTA DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
109
-
GeForce GTX 1070
67
FPS (higher is better)
Ultra High Quality, TAA, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
120
-
GeForce GTX 1070
77
FPS (higher is better)
Ultra High Quality TAA, Bahrain, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
121
-
GeForce GTX 1070
69
FPS (higher is better)
Windows 10 x64, Ultra quality, DirectX12
-
GeForce GTX 1080 Ti
36
-
GeForce GTX 1070
23
FPS (higher is better)
Very High Quality TAA, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
109
-
GeForce GTX 1070
72
FPS (higher is better)
Highest quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
119
-
GeForce GTX 1070
77
FPS (higher is better)
Ultra quality DirectX12 Windows10 x64
-
GeForce GTX 1080 Ti
89
-
GeForce GTX 1070
56
FPS (higher is better)
Ultra Quality,DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
96
-
GeForce GTX 1070
52
FPS (higher is better)
Ultra, TSSAA 8tx, ASync on, Vsync off, VULKAN, Windows 10 x64
-
GeForce GTX 1080 Ti
188
-
GeForce GTX 1070
124
FPS (higher is better)
Ultra quality,TTA,Melbourne,DirectX11,Windows 10 x64
-
GeForce GTX 1080 Ti
137
-
GeForce GTX 1070
88
FPS (higher is better)
Ultra quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
101
-
GeForce GTX 1070
67
FPS (higher is better)
Ultra High Quality, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
66
-
GeForce GTX 1070
37
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
104
-
GeForce GTX 1070
68
FPS (higher is better)
DX11, Very High Settings
-
GeForce GTX 1080 Ti
101
-
GeForce GTX 1070
65
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
116
-
GeForce GTX 1070
79
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
82
-
GeForce GTX 1070
53
FPS (higher is better)
Very high Quality, DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
86
-
GeForce GTX 1070
59
FPS (higher is better)
DX11, Max Details, 16:1 AF, 2xMSAA
-
GeForce GTX 1080 Ti
144
-
GeForce GTX 1070
101
FPS (higher is better)
Ultra quality,16:1 HQ-AF,DirectX 12, windows 10 x64
-
GeForce GTX 1080 Ti
130
-
GeForce GTX 1070
87
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
101
-
GeForce GTX 1070
65
FPS (higher is better)
Very high quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
74
-
GeForce GTX 1070
46
FPS (higher is better)
Ultra Detail,16:1 AF, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
57
-
GeForce GTX 1070
34
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
37
-
GeForce GTX 1070
21
FPS (higher is better)
Ultra Quality, HR Textures, DirectX11, Windows 10 x64
-
GeForce GTX 1080 Ti
89
-
GeForce GTX 1070
55
FPS (higher is better)
UltraTX Max Quality, Vulkan, Windows 10 x64
-
GeForce GTX 1080 Ti
50
-
GeForce GTX 1070
32
FPS (higher is better)
Max Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
104
-
GeForce GTX 1070
60
FPS (higher is better)
Maximun Quality, DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
120
-
GeForce GTX 1070
74
FPS (higher is better)
Very High Details, Pure Hair On, FXAA/HBAO+ enabled, 16x AF, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
121
-
GeForce GTX 1070
73
FPS (higher is better)
Highest Details, Pure hair, HBAO+, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
78
-
GeForce GTX 1070
49
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
115
-
GeForce GTX 1070
72
FPS (higher is better)
Ultra quality DirectX12 Windows10 x64
-
GeForce GTX 1080 Ti
126
-
GeForce GTX 1070
82
FPS (higher is better)
Ultra Quality, DirectX12, Async Compute ,Windows 10×64
-
GeForce GTX 1080 Ti
121
-
GeForce GTX 1070
73
FPS (higher is better)
DX11,Max Details, 16:1 HQ-AF, +AA
-
GeForce GTX 1080 Ti
108
-
GeForce GTX 1070
65
FPS (higher is better)
DX11, Max Details, 16:1 AF
-
GeForce GTX 1080 Ti
97
-
GeForce GTX 1070
59
FPS (higher is better)
Ultra Quality, Windows 10 x64
-
GeForce GTX 1080 Ti
76
-
GeForce GTX 1070
48
FPS (higher is better)
Main Leben! quality preset- Vulkan Windows 10×64
-
GeForce GTX 1080 Ti
99
-
GeForce GTX 1070
63
FPS (higher is better)
DX11, Max Detail, 2xMSAA 16xAF
-
GeForce GTX 1080 Ti
113
-
GeForce GTX 1070
66
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
33
-
GeForce GTX 1070
21
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
73
-
GeForce GTX 1070
47
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
60
-
GeForce GTX 1070
37
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
36
-
GeForce GTX 1070
22
FPS (higher is better)
Ultra quality TTA DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
68
-
GeForce GTX 1070
40
FPS (higher is better)
Ultra High Quality, TAA, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
70
-
GeForce GTX 1070
43
FPS (higher is better)
Ultra High Quality TAA, Bahrain, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
72
-
GeForce GTX 1070
46
FPS (higher is better)
Windows 10 x64, Ultra quality, DirectX12
-
GeForce GTX 1080 Ti
18
-
GeForce GTX 1070
10
FPS (higher is better)
Very High Quality TAA, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
61
-
GeForce GTX 1070
39
FPS (higher is better)
Highest quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
71
-
GeForce GTX 1070
44
FPS (higher is better)
Ultra quality DirectX12 Windows10 x64
-
GeForce GTX 1080 Ti
46
-
GeForce GTX 1070
28
FPS (higher is better)
Ultra Quality,DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
57
-
GeForce GTX 1070
32
FPS (higher is better)
Ultra, TSSAA 8tx, ASync on, Vsync off, VULKAN, Windows 10 x64
-
GeForce GTX 1080 Ti
98
-
GeForce GTX 1070
64
FPS (higher is better)
Ultra quality,TTA,Melbourne,Windows 10 x64
-
GeForce GTX 1080 Ti
76
-
GeForce GTX 1070
55
FPS (higher is better)
Ultra quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
53
-
GeForce GTX 1070
34
FPS (higher is better)
Ultra High Quality, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
42
-
GeForce GTX 1070
26
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
58
-
GeForce GTX 1070
37
FPS (higher is better)
DX11, Very High Settings
-
GeForce GTX 1080 Ti
58
-
GeForce GTX 1070
35
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
57
-
GeForce GTX 1070
41
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
46
-
GeForce GTX 1070
29
FPS (higher is better)
Very high Quality, DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
52
-
GeForce GTX 1070
34
FPS (higher is better)
DX11, Max Details, 16:1 AF, 2xMSAA
-
GeForce GTX 1080 Ti
78
-
GeForce GTX 1070
48
FPS (higher is better)
Ultra quality,16:1 HQ-AF,DirectX 12, windows 10 x64
-
GeForce GTX 1080 Ti
78
-
GeForce GTX 1070
52
FPS (higher is better)
Ultra Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
55
-
GeForce GTX 1070
35
FPS (higher is better)
Very high quality DirectX11 Windows10 x64
-
GeForce GTX 1080 Ti
37
-
GeForce GTX 1070
22
FPS (higher is better)
Ultra Detail,16:1 AF, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
36
-
GeForce GTX 1070
21
FPS (higher is better)
Ultra Quality, DirectX11, Windows 10×64
-
GeForce GTX 1080 Ti
22
-
GeForce GTX 1070
12
FPS (higher is better)
Ultra Quality, HR Textures, DirectX11, Windows 10 x64
-
GeForce GTX 1080 Ti
53
-
GeForce GTX 1070
32
FPS (higher is better)
UltraTX Max Quality, Vulkan, Windows 10 x64
-
GeForce GTX 1080 Ti
31
-
GeForce GTX 1070
19
FPS (higher is better)
Max Quality, DirectX12, Windows 10×64
-
GeForce GTX 1080 Ti
52
-
GeForce GTX 1070
33
FPS (higher is better)
Maximun Quality, DX11, Windows 10 x64
-
GeForce GTX 1080 Ti
61
-
GeForce GTX 1070
37
FPS (higher is better)
Very High Details, Pure Hair On, FXAA/HBAO+ enabled, 16x AF, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
60
-
GeForce GTX 1070
38
FPS (higher is better)
Highest Details, Pure hair, HBAO+, DirectX12, Windows 10 x64
-
GeForce GTX 1080 Ti
42
-
GeForce GTX 1070
25
FPS (higher is better)
Ultra Quality, DirectX 12, Windows 10 x64
-
GeForce GTX 1080 Ti
68
-
GeForce GTX 1070
40
FPS (higher is better)
Ultra quality DirectX12 Windows10 x64
-
GeForce GTX 1080 Ti
68
-
GeForce GTX 1070
41
FPS (higher is better)
Ultra Quality, DirectX12, Async Compute ,Windows 10×64
-
GeForce GTX 1080 Ti
71
-
GeForce GTX 1070
41
FPS (higher is better)
DX11,Max Details, 16:1 HQ-AF, +AA
-
GeForce GTX 1080 Ti
66
-
GeForce GTX 1070
39
FPS (higher is better)
DX11, Max Details, 16:1 AF
-
GeForce GTX 1080 Ti
56
-
GeForce GTX 1070
34
FPS (higher is better)
Ultra Quality, Windows 10 x64
-
GeForce GTX 1080 Ti
43
-
GeForce GTX 1070
25
FPS (higher is better)
Main Leben! quality preset- Vulkan Windows 10×64
-
GeForce GTX 1080 Ti
62
-
GeForce GTX 1070
39
FPS (higher is better)
VS | ||
GeForce GTX 1080 Ti | GeForce RTX 2070 Super |
VS | ||
GeForce GTX 1080 Ti | Radeon RX 5700 XT |
VS | ||
GeForce GTX 1070 | Radeon RX 5500 XT |
VS | ||
GeForce GTX 1070 | GeForce GTX 1660 SUPER |
VS | ||
GeForce RTX 3060 Ti | GeForce RTX 2080 Super |
VS | ||
GeForce RTX 2080 Super | TITAN V |
Please enable JavaScript to view the comments powered by Disqus.
Nvidia GeForce GTX 1080 vs 1070: Which is right for you?
There’s no doubt that Nvidia is raising its game when it comes to high-end graphics. Both of its recent releases have been barnstormers, and there’s certainly no question over where you should look if you’re searching for an enthusiast GPU.
At the top end, the choice isn’t between Nvidia or AMD, but which GeForce card to opt for. There’s the flagship GTX 1080, which deploys the full clout of the Pascal architecture – but it costs almost £600. If your pockets aren’t that deep then there’s the GTX 1070, which comes in at a more palatable £380 – but it isn’t as powerful.
TrustedReviews put both of these GPUs through a comprehensive set of benchmarks to find out which is best – and I’ve taken a deep dive into board partner cards, prices and overclocking too. Of course, you know which is the more powerful of the two, but hopefully the comparisons outlined below will help you to decide which card is best for your needs. Let’s get started.
If you want to read our individual reviews, you can click here for the GTX 1080 and GTX 1070 reviews.
Video: Nvidia GeForce GTX 1080 review
Nvidia GeForce GTX 1070 vs 1080 – Specs and Technology
The two GTX cards share the same architecture, but they’re designed for different scenarios. The range-topping GTX 1080 is built for 4K, multi-monitor and VR. The GTX 1070 has enough grunt to handle VR and 1440 playback, but it isn’t quite good enough for smooth 4K gaming.
Th Pascal architecture around which both cards are based is a remarkable bit of design. Nvidia has slimmed down its manufacturing process from 28nm to 16nm, a shrinkage that has allowed the firm to fit more transistors into smaller spaces – and to deploy them on fins, rather than on mere horizontal planes.
The result is that Nvidia is achieving far more with much less: the firm’s new cards include millions more transistors than previous GPUs, and on significantly smaller bits of silicon.
The smoother flow of electricity allows for better GPU performance alongside surprisingly low power consumption. The two new cards deploy 7.2 billion transistors on a 314mm2 die, with peak power consumption figures of 150W and 180W. Their predecessors used 5.2 billion transistors on a 398mm2 die and drew a peak of 145W and 165W from the mains.
Related: The best gaming PC specs to build yourself from £500
The GTX 1080 tops the range with 2,560 CUDA cores, while the GTX 1070 arrives with 1,920. Both cards tower over their predecessors: the GTX 980 had 2,048, while the GTX 970 had 1,664.
Video: Nvidia GeForce GTX 1070 review
VI Video was already generated for this page.
The clock speeds are given a huge boost, too. The GTX 1080 zips along at 1,607MHz and the GTX 1070 is just 101MHz slower – both figures are hundreds of megahertz ahead of last year’s cards.
The shared architecture across the cards mean they share Nvidia’s new software features. One of the key inclusions is “pre-emption”, which allows Nvidia’s card to pick and choose between graphics and computing workloads simultaneously.
Both cards also have Lens Matched Shading, which saves resources by not rendering pixels that won’t be seen by the user. There’s simultaneous multi-projection, which allows the GPU to render a scene in as many as 16 different viewpoints – a boon for VR.
Related: Best graphics cards to buy
Many of these features won’t be used to their full potential right now, but future games development will no doubt take advantage, especially when APIs such as DirectX 12 and Vulkan are better supported.
The two cards diverge in the memory department. The GTX 1080 has 8GB of GDDR5X memory, while the GTX 1070 has 8GB of bog-standard GDDR5 RAM. The former memory is faster, with a 10,000MHz clock compared to the 8,000MHz in the GTX 1070. The GDDR5X memory has a 320-bit bus – wider than the 256-bit included on the GTX 1070.
Nvidia GeForce GTX 1070 vs 1080 – Testing Methodology
I benchmarked the GTX 1070 and GTX 1080 on TrustedReviews’ test rig, which has been designed to match the specifications of a standard enthusiast gaming PC. It features the following components:
- Motherboard: Asus Z170-Deluxe
- Processor: Intel Core i5-6600K (not overclocked)
- RAM: Corsair Vengeance 2666MHz, 16GB DDR4
- Cooler: Corsair H60 liquid cooler
- PSU: Corsair CX750M
- SSD: Samsung 850 EVO
- OS: Windows 10 Pro 64-bit
I’ve tested these powerful cards with five different games. Each title is run at its highest settings, and I’ve tested each game at 1,920 x 1,080, 2,560 x 1,440 and 3,840 x 2,160 – 4K.
I’ve also used a selection of synthetic benchmarks, with 3DMark’s demanding Fire Strike test alongside benchmarks to measure power consumption and peak temperature.
DiRT Rally
Ultra at 1,920 x 1,080 average
GTX 1070: 134. 7
GTX 1080: 154.8
Ultra at 2,560 x 1,440, average
GTX 1070: 97.4
GTX 1080: 122.07
Ultra at 3,840 x 2,160, average
GTX 1070: 52.5
GTX 1080: 63.2
There’s no denying that the GTX 1080 is faster than the GTX 1070, but there’s also no denying that both cards have the power to play DiRT Rally at any resolution.
That’s no surprise, though: this is the easiest benchmark in the slate of test games. It’s fully representative of gameplay, and tests a GPU with complex lighting and rapid texture movement.
Both cards destroyed the 1080p benchmark with average frame rates of 134.7fps and 154.8fps, and the GTX 1080 continued to average a three-figure result at 1440p with 122.07fps. The GTX 1070 was no slouch, either – it hit 97.4fps in the same run.
The two Nvidia cards handle 3,840 x 2,160 with aplomb. The GTX 1070’s average of 52.5fps is excellent, and the GTX 1080 was almost 11 frames faster. Crucially, the pricier card got beyond the 60fps barrier that heralds butter-smooth gameplay.
Middle-earth: Shadow of Mordor
Ultra at 1,920 x 1,080 average
GTX 1070: 131.3
GTX 1080: 160.3
Ultra at 2,560 x 1,440, average
GTX 1070: 89.8
GTX 1080: 112.3
Ultra at 3,840 x 2,160, average
GTX 1070: 46.7
GTX 1080: 54.9
This game is tougher thanks to a multitude of environmental effects including weather, explosions and fire.
The more challenging game didn’t stop Nvidia’s latest cards blowing away my 1080p test. Both flew past 130fps averages in the 1080p benchmark, and the GTX 1080 continued its good form at 2,560 x 1,440, where it averaged 112.32fps. The cheaper GeForce card impressed, too, with an average of 89.8fps.
The two cards continued to perform well at 4K. The GTX 1080’s 54.9fps average is almost 10 frames beyond its cheaper stablemate, but I’ve no qualms about the GTX 1070’s ability to run this game smoothly at 4K.
Grand Theft Auto V
Ultra at 1,920 x 1,080 average
GTX 1070: 104.2
GTX 1080: 113.4
Ultra at 2,560 x 1,440, average
GTX 1070: 74.9
GTX 1080: 89.3
Ultra at 3,840 x 2,160, average
GTX 1070: 39.3
GTX 1080: 47.3
GTA V’s benchmark is a hugely demanding test, with numerous scenes that cover driving, flying and plenty of other scenarios. Graphically, it’s a demanding game, and here I test with every option run at maximum.
This is another game where both cards handled every resolution, but it is in this trickier title where one card slipped below a 40fps average.
The GTX 1070 averaged 39.3fps in GTA V at 4K, which is almost 10 frames behind the GTX 1080 – a playable score, but still a significant gap between the cards.
There wasn’t as much space between the GPUs at 1440p, where the GTX 1070 registered a sterling 74. 9fps average and the GTX 1080 delivered an 89.3fps result. And at 1080p, both cards excelled with averages beyond 100fps.
It’s worth looking beyond the frame rates to see how the GTX 1080 flexes its extra CUDA core muscles. The GTX 1070 is only 8.11% behind the GTX 1080 at 1080p, but that gap increases to 16.13% at 1440p – and 16.91% at 4K.
Hitman
Max Settings at 1,920 x 1,080, average
GTX 1070: 81.7
GTX 1080: 81.5
Max Settings at 2,560 x 1,440, average
GTX 1070: 69.8
GTX 1080: 84
Max Settings at 3,840 x 2,160, average
GTX 1070: 29.8
GTX 1080: 47.7
This benchmark stresses a PC’s processor and graphics card with a potent mix of objects, NPCs and lighting effects, and here it’s run at peak settings.
I observed the GTX 1080’s widening lead across resolutions in GTA V, and that pattern is even more obvious in Hitman. There’s basically no difference between the two GPUs at 1080p, but the GTX 1080 is 16.93% faster at 1440p – and then 37.53% quicker at 3,840 x 2,160.
This isn’t the only bit of bad news for the GTX 1070. It rattled through Hitman’s 1080p and 1440p tests at good averages of 81.7fps and 69.8fps, but it faltered at 4K with an average of 29.8fps. That’s below the key 30fps figure, and its minimum frame rate will be even lower – which means that the game will stutter at this demanding resolution.
The GTX 1080 had no such problems. It blitzed the 1080p and 1440p tests at 81.5fps and 84.03fps – its increase in speed a clear demonstration of the card flexing its muscles; and it handled 4K at 47.7fps.
Rise of the Tomb Raider
Max Settings at 1,920 x 1,080 average
GTX 1070: 97.9
GTX 1080: 135.8
Max Settings at 2,560 x 1,440, average
GTX 1070: 65.6
GTX 1080: 92.5
Max Settings at 3,840 x 2,160, average
GTX 1070: 34
GTX 1080: 48. 3
The intensive weather and lighting effects in this benchmark will strain even the beefiest graphics core, and I’ve run the game with every option turned up to the maximum level.
In these tests the GTX 1080 rose to the occasion, with a 4K average of 48.3fps – and it ran at nearly 100fps when I dropped the resolution to 2,560 x 1,440.
The GTX 1070 performed well, too – and certainly improved on its Hitman frame rates. Its 4K average of 34fps is back on the right side of 30fps, and it breezed through 60fps at 1440p. It almost hit 100fps at 1080p, too.
In addition, the GTX 1070 was consistently slower than the GTX 1080 in this test, but the gap between the two cards sat at just below 30% in every test. That’s a better bill of health than its scores in the previous two games, where the GTX 1080 deployed its better memory and larger complement or stream processors to open a larger gap with every resolution increase.
Synthetic Benchmarks, Power and Heat
3D Mark Fire Strike Ultra
GTX 1070: 3,953
GTX 1080: 4,884
Peak power:
GTX 1070: 229W
GTX 1080: 286W
Peak temperature:
GTX 1070: 74°C
GTX 1080: 75°C
The 3DMark: Fire Strike test demonstrates the gulf in power between these two excellent cards. The GTX 1070 scored 3,953, but the GTX 1080 managed 4,884. The extra stream processors, higher clock and better memory clearly work wonders.
The Fire Strike test also provides a firm demonstration of just how much better the new Nvidia hardware is when compared to earlier cards. The GTX 970 scored just 2,767 in this test, while the GTX 980 could manage only 3,286.
My test rig consumed 229W with the GTX 1070 installed and 286W with the GTX 1080 on-board. These are fantastic figures considering the power on offer from these cards: the GTX 1070’s power draw is actually lower than the 260W requirement of the GTX 970, and the GTX 1080 is only 16W ahead of my GTX 980 rig.
These figures will be even better when compared to older GPUs, and there are several benefits to having a more efficient GPU installed: less electricity is consumed, less heat is generated, and your PC will be quieter.
There’s little to choose between peak temperatures – no surprise, seeing as I tested Nvidia’s Founders Edition hardware, which is the same across both chips. The GTX 1080’s 75°C peak was one degree warmer than the GTX 1070.
Performance Conclusions
There’s no doubt about it: Nvidia’s latest two GPU releases secure its position at the top of the graphics market – at least until AMD unveils some more powerful cards based on its new Polaris architecture.
The GTX 1070 and GTX 1080 are both hugely powerful. They both rattled through 1080p and 1440p benchmarks without breaking a sweat, and both have enough power to handle VR.
Head towards the high-end, though, and the GTX 1080 starts to justify its higher price. The GTX 1070 dipped below 30fps in one 4K test, and its lower averages in some of those benchmarks mean its minimums will be slower – and that means juddering gameplay. The GTX 1080 had no such problems, with far smoother 4K performance.
I also observed the GTX 1080 opening wider leads on its stablemate as resolutions became trickier. That’s testament to its superior specification, and it means the GTX 1080 is a better bet for 4K and multi-monitor setups – and for VR, where its extra power adds a layer of future-proofing.
Both cards easily outpaced their predecessors and both did so with impressive noise and power consumption figures.
Nvidia has done a sterling job with the Pascal architecture, and it means these two cards are both worth considering. The GTX 1070 is a superb choice for 1080p and 1440p gaming, while the GTX 1080 is fantastic for 4K, multi-monitor setups and smooth VR.
Overclocking and SLI
Nvidia reckons there’s ample headroom for overclocking on both cards thanks to GPU Boost 3.0, which provides more granular control over core and memory frequencies and voltages.
It was possible to achieve decent gains from both cards. I added 220MHz and 260MHz to the GTX 1070’s core and memory clocks, which saw an average improvement of around 6fps in my games tests. The GTX 1080 saw its core and memory clocks rise by 200MHz and 189MHz, which delivered about five more frames in the test games.
The situation surrounding SLI is a little trickier. Nvidia is allowing gamers to use two cards in SLI, but if you’d like to go further then you’ll have to register with Nvidia to receive an unlock code.
This is a new approach, but I can’t see it hampering many gamers – the performance of these cards mean that there’s little need to go beyond two GPUs, and the driver issues and diminishing returns of three- and four-card SLI means I can’t wholeheartedly recommend that approach.
Other Things to Consider
Nvidia launched both of these GPUs with its Founders Edition hardware, which was far more expensive than board partner cards yet actually offered very little. That extra spend got you the kudos of being first in the queue alongside Nvidia’s admittedly excellent metallic card design, but nothing else.
Thankfully, there’s now no need to spend all that extra cash on the Founders Edition cards – board partners have unleashed their own versions of the new GPUs.
There’s already huge variety in the marketplace. Prices for air-cooled cards range from £380 to £500, and beyond that there are cards with waterblocks fitted for liquid cooling. Even the cheapest cards come with modest overclocks, and spending around £420 could net you a card with a GPU at 1,620MHz or 1,670MHz and memory overclocked to 8,500MHz.
Many GTX 1070s use Nvidia’s sturdy reference design, but plenty more deploy a greater number of fans and different heatsinks. There’s even a tiny mini-ITX version, and a card with a pre-built water-cooling unit attached.
Unlike the GTX 1070, the GTX 1080 doesn’t have smaller versions of the card available, but the market is well stocked with reference and third-party designs. Prices range between £590 and £750, and overclocked models are common. These tweaked cores often run at speeds beyond 1,700MHz, with memory tweaked to 10,500MHz.
Verdict
There’s plenty to like about both of these GPUs – and they’re both worth considering for different scenarios.
The GTX 1070 is an exceptional card for 1080p and 1440p gaming, and it has ample power for VR. It does this while consuming less power than its predecessor, and I’ve seen that overclocking yields impressive results too.
The GTX 1080 is more expensive, but it’s the best graphics card on the market right now – and that makes it worth the extra cash. It’s unbeatable at 4K, and it has the grunt for multi-monitor setups and VR too. If you’re going to play games at the high-end, this is the card to buy.
Related: Best graphics cards to buy
GeForce GTX 1070 SLI vs GeForce GTX 1080 Ti Graphics cards Comparison
When choosing between GeForce GTX 1070 SLI and GeForce GTX 1080 Ti, it is worth examining the specifications of the models in detail. Do they meet the recommended requirements of modern games and software? Storage capacity, form factor, TDP, available ports, warranty and manufacturer support are all important. For example, the size of a PC case can limit the maximum thickness and length of the card. Often, instead of the factory overclocked card and RGB backlight, it is better to choose a reference model with a more efficient GPU. And make sure that your current power supply unit has the correct connection pins (using adapters is not recommended). This GPUs compare tool is meant to help you to choose the best graphics card for your build. Let’s find out the difference between GeForce GTX 1070 SLI and GeForce GTX 1080 Ti.
GeForce GTX 1070 SLI
GeForce GTX 1080 Ti
Check Price
Main Specs
GeForce GTX 1070 SLI | GeForce GTX 1080 Ti | |
Power consumption (TDP) | 300 Watt | 250 Watt |
Interface | PCIe 3.0 x16 | |
Supplementary power connectors | 1x 6-pin + 1x 8-pin | |
Memory type | GDDR5 | GDDR5X |
Maximum RAM amount | 2x 8 GB | 11 GB |
Display Connectors | 1x HDMI, 3x DisplayPort | |
Recommended system power (PSU) | 600 Watt | |
Check Price |
- GeForce GTX 1070 SLI has 20% more power consumption, than GeForce GTX 1080 Ti.
- GeForce GTX 1080 Ti has 9 GB more memory, than GeForce GTX 1070 SLI.
- Both cards are used in Desktops.
- GeForce GTX 1070 SLI and GeForce GTX 1080 Ti are build with Pascal architecture.
- Core clock speed of GeForce GTX 1070 SLI is 25 MHz higher, than GeForce GTX 1080 Ti.
- GeForce GTX 1070 SLI and GeForce GTX 1080 Ti are manufactured by 16 nm process technology.
- Memory clock speed of GeForce GTX 1080 Ti is 3000 MHz higher, than GeForce GTX 1070 SLI.
Game benchmarks
Assassin’s Creed OdysseyBattlefield 5Call of Duty: WarzoneCounter-Strike: Global OffensiveCyberpunk 2077Dota 2Far Cry 5FortniteForza Horizon 4Grand Theft Auto VMetro ExodusMinecraftPLAYERUNKNOWN’S BATTLEGROUNDSRed Dead Redemption 2The Witcher 3: Wild HuntWorld of Tanks | ||
high / 1080p | 75−80 | 75−80 |
ultra / 1080p | 55−60 | 55−60 |
QHD / 1440p | 45−50 | 45−50 |
4K / 2160p | 30−35 | 30−35 |
low / 720p | 100−105 | 100−105 |
medium / 1080p | 90−95 | 90−95 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Assassin’s Creed Odyssey. | ||
high / 1080p | 120−130 | 120−130 |
ultra / 1080p | 110−120 | 110−120 |
QHD / 1440p | 90−95 | 90−95 |
4K / 2160p | 55−60 | 55−60 |
low / 720p | 160−170 | 160−170 |
medium / 1080p | 130−140 | 130−140 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Battlefield 5. | ||
low / 768p | 45−50 | 45−50 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Call of Duty: Warzone. | ||
low / 768p | 250−260 | 250−260 |
medium / 768p | 230−240 | 230−240 |
QHD / 1440p | 150−160 | 150−160 |
4K / 2160p | 100−110 | 100−110 |
high / 768p | 220−230 | 220−230 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Counter-Strike: Global Offensive. | ||
low / 768p | 70−75 | 70−75 |
medium / 1080p | 50−55 | 50−55 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Cyberpunk 2077. | ||
low / 768p | 120−130 | 120−130 |
medium / 768p | 110−120 | 110−120 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Dota 2. | ||
high / 1080p | 100−110 | 100−110 |
ultra / 1080p | 95−100 | 95−100 |
QHD / 1440p | 80−85 | 80−85 |
4K / 2160p | 40−45 | 40−45 |
low / 720p | 120−130 | 120−130 |
medium / 1080p | 100−110 | 100−110 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Far Cry 5. | ||
high / 1080p | 160−170 | 160−170 |
ultra / 1080p | 130−140 | 130−140 |
QHD / 1440p | 90−95 | 90−95 |
4K / 2160p | 21−24 | 21−24 |
low / 720p | 270−280 | 270−280 |
medium / 1080p | 190−200 | 190−200 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Fortnite. | ||
high / 1080p | 130−140 | 130−140 |
ultra / 1080p | 110−120 | 110−120 |
QHD / 1440p | 95−100 | 95−100 |
4K / 2160p | 60−65 | 60−65 |
low / 720p | 170−180 | 170−180 |
medium / 1080p | 140−150 | 140−150 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Forza Horizon 4. | ||
low / 768p | 170−180 | 170−180 |
medium / 768p | 160−170 | 160−170 |
high / 1080p | 140−150 | 140−150 |
ultra / 1080p | 85−90 | 85−90 |
QHD / 1440p | 75−80 | 75−80 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Grand Theft Auto V. | ||
high / 1080p | 70−75 | 70−75 |
ultra / 1080p | 60−65 | 60−65 |
QHD / 1440p | 45−50 | 45−50 |
4K / 2160p | 30−33 | 30−33 |
low / 720p | 140−150 | 140−150 |
medium / 1080p | 95−100 | 95−100 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Metro Exodus. | ||
low / 768p | 120−130 | 120−130 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Minecraft. | ||
high / 1080p | 140−150 | 140−150 |
ultra / 1080p | 110−120 | 110−120 |
4K / 2160p | 18−20 | 18−20 |
low / 720p | 160−170 | 160−170 |
medium / 1080p | 160−170 | 160−170 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in PLAYERUNKNOWN’S BATTLEGROUNDS. | ||
high / 1080p | 70−75 | 70−75 |
ultra / 1080p | 45−50 | 45−50 |
QHD / 1440p | 35−40 | 35−40 |
4K / 2160p | 24−27 | 24−27 |
low / 720p | 130−140 | 130−140 |
medium / 1080p | 100−110 | 100−110 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in Red Dead Redemption 2. | ||
low / 768p | 290−300 | 290−300 |
medium / 768p | 220−230 | 220−230 |
high / 1080p | 140−150 | 140−150 |
ultra / 1080p | 75−80 | 75−80 |
4K / 2160p | 50−55 | 50−55 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in The Witcher 3: Wild Hunt. | ||
low / 768p | 350−400 | 350−400 |
ultra / 1080p | 160−170 | 160−170 |
GeForce GTX 1070 SLI and GeForce GTX 1080 Ti have the same average FPS in World of Tanks. |
Full Specs
GeForce GTX 1070 SLI | GeForce GTX 1080 Ti | |
Architecture | Pascal | Pascal |
Code name | Pascal GP104 SLI | GP102 |
Type | Desktop | Desktop |
Release date | 16 August 2016 | 28 February 2017 |
Pipelines | 3840 | 3584 |
Core clock speed | 1506 MHz | 1481 MHz |
Boost Clock | 1683 MHz | 1600 MHz |
Transistor count | 14400 Million | 11,800 million |
Manufacturing process technology | 16 nm | 16 nm |
Texture fill rate | 354. 4 | |
Floating-point performance | 11,340 gflops | |
Length | 10.5″ (26.7 cm) | |
Memory bus width | 256 Bit | 352 Bit |
Memory clock speed | 8000 MHz | 11000 MHz |
Memory bandwidth | 484.4 GB/s | |
Shared memory | — | — |
G-SYNC support | + | + |
VR Ready | + | |
DirectX | DirectX 12_1 | 12 (12_1) |
Shader Model | 6.4 | |
OpenGL | 4.5 | |
OpenCL | 1.2 | |
Vulkan | + | 1. 2.131 |
CUDA | + | + |
Monero / XMR (CryptoNight) | 0.76 kh/s | |
SLI options | + | + |
Multi monitor support | + | |
Bitcoin / BTC (SHA256) | 1427 Mh/s | |
Decred / DCR (Decred) | 4.6 Gh/s | |
Ethereum / ETH (DaggerHashimoto) | 35 Mh/s | |
Zcash / ZEC (Equihash) | 630 Sol/s | |
GPU Boost | 3.0 | |
Siacoin / SC (Sia) | 2.96 Gh/s | |
Check Price |
Similar compares
- GeForce GTX 1070 SLI vs GeForce GTX 1070 SLI mobile
- GeForce GTX 1070 SLI vs TITAN RTX
- GeForce GTX 1080 Ti vs GeForce GTX 1070 SLI mobile
- GeForce GTX 1080 Ti vs TITAN RTX
- GeForce GTX 1070 SLI vs GeForce RTX 2080
- GeForce GTX 1070 SLI vs GeForce GTX 1080 SLI mobile
- GeForce GTX 1080 Ti vs GeForce RTX 2080
- GeForce GTX 1080 Ti vs GeForce GTX 1080 SLI mobile
Nvidia GeForce GTX 1080 Ti vs 1080 vs 1070 vs 1060 vs 1050
If you’re about to buy a
gaming laptop or a new graphics card for your PC, then you’ll be looking at Nvidia’s 10-series GPUs. The full range now includes the 1080 Ti, 1080, 1070, 1060 and entry-level 1050. AMD’s current
Radeon RX range competes with Nvidia only at the lower end. The
Radeon RX Vega is coming soon.
The GeForce GTX 10-series cards are all fast, but as well as being great for the latest PC games, they’re also ideal if you want to hook up a
VR headset.
The ‘prosumer’ Titan Xp is not included here but we have compared it with the 1080 Ti in our
Titan Xp vs 1080 Ti head to head.
You’ll find full reviews of all of these in our
best graphics cards round-up and more about the cards’
release date, UK price and availability.
How much do they cost?
The cards are all available now, with prices ranging between £99 and £850 depending on model and supplier. The table below summarises the prices you can expect to pay for the Nvidia reference card (the Founders Edition) and cards made by partners including Asus, MSI, XFX, Zotac and others.
Founders Edition price |
Average price |
|
GTX 1080 Ti |
£699 / $699 |
£800 / $800 |
GTX 1080 |
£545 / $549 |
£570 / $535 |
GTX 1070 |
£395 / $399 |
£450 / $400 |
GTX 1060 |
£275 / $299 |
£220 / $270 |
GTX 1050 Ti |
N/A |
£150 / $150 |
GTX 1050 |
N/A |
£115 / $110 |
The Founders Edition cards aren’t always cheaper than overclocked third-party cards. The average prices we’ve listed here are for overclocked cards from partners, but you can save a little money if you buy a card running at Nvidia’s standard speeds.
In the UK, you can buy these cards from a variety of UK retailers including:
Overclockers UK,
Ebuyer,
Scan,
Amazon,
Maplin and
Currys.
You can buy Founders Editions directly from
Nvidia’s website.
GeForce 10-series in laptops
Obviously these prices doesn’t apply if you’re considering a gaming laptop that has the graphics processor built in. However, there are a small number of laptops, including the
Razer Blade Stealth, which optionally let you connect a full-size PCI-express graphics card in an external housing.
Crucially, this means you can upgrade your laptop’s graphics card – something that isn’t possible with most gaming laptops.
Read our
buyer’s guide for gaming laptops before you spend your hard-earned cash.
How do their specifications differ?
Here’s a summary of the cards’ main specifications:
1080 Ti |
1080 |
1070 |
1060 |
1050 Ti |
1050 |
|
CUDA Cores |
3584 |
2560 |
1920 |
1280 |
768 |
640 |
Core Clock |
1480MHz |
1607MHz |
1506MHz |
1506MHz |
1290MHz |
1354MHz |
Boost Clock |
1582MHz |
1733MHz |
1683MHz |
1708MHz |
1392MHz |
1455Mhz |
VRAM |
11GB |
8GB |
8GB |
6GB |
4GB |
2GB |
Memory Clock |
11GB/s |
10Gb/s |
8GB/s |
8GB/s |
7Gb/s |
7Gb/s |
Memory Bus Width |
384-bit |
256-bit |
256-bit |
192-bit |
128-bit |
128-bit |
Memory Bandwidth |
484GB/s |
320GB/s |
256GB/s |
192GB/s |
112GB/s |
112GB/s |
TDP |
250W |
180W |
150W |
120W |
75W |
75W |
Power connector(s) |
1x 8-pin, 1x 6-pin |
1x 8-pin |
1x 8-pin |
1x 6-pin |
None |
None |
SLI support |
Yes |
Yes |
Yes |
No |
No |
No |
What is GDDR5X?
Apart from the two GTX 1080 cards, the range all use GDDR5 memory. But the top two use GDDR5X which allows double the theoretical bandwidth speed of traditional GDDR5 memory.
The higher memory bandwidth of the GTX 1080 (and Ti) allows it to run a third faster than the GTX 1070, GTX 1060 and other GDDR5 cards. Bottom line: they perform better.
What features do they have?
Every 10-series card is based on Nvidia’s Pascal platform, which means they all support the same set of features. Performance is the only real differentiator, although certain cards lower in the range are available in ‘mini’ versions which will fit into small PC cases, such as the
Zotac 1050 Ti.
Power
From the specifications table above, you’ll note that the power requirements decrease as you go down the range. The 1050 and 1050 Ti only require power from the PCIe slot itself and don’t need a separate power connector from your power supply. This makes them a reasonable upgrade option if you don’t want to buy and install a higher-wattage PSU.
Shadowplay
The cards have the same streaming-, game recording- and light-customisation options through Nvidia’s Shadowplay software.
Ansel
There’s also support for
Nvidia Ansel on all cards in the range. Ansell allows you to take in-game pictures in 3D which can then be viewed in a suitable viewer, such as a VR headset.
Fast Sync
The cards also have an advanced and improved version of V-sync, which locks the graphic card’s output to your monitor’s refresh rate. In the past V-sync has negatively affected the latency of a monitor.
Nvidia claims that Fast Sync will eliminate tearing while maintaining the low latency benefits. The graph shows the latency differences between V-sync and Fast Sync in Counter-Strike: Global Offensive.
Which card should I buy?
If you want the best performance, the 1080 Ti is the obvious choice. However, not everyone needs this much power. Really, the 1080 Ti is only for those gaming in 4K at ‘ultra’ quality settings or those who have VR headset.
The GTX 1060 arguably provides the best bang for your buck in the range. It will happily play the latest titles in 1080p at maximum quality and can even handle 2560×1440.
But the 1050 (and Ti variant) are great upgrades for older PCs as they will also handle modern games at 1080p, and for between £100 and £150 represent good value as well.
Of course, before choosing a specific card, you should also consider AMD’s options which are also great value for 1080p gaming. For the most up to date information, see our list of the
best graphics cards.
If you’re unsure of how to fit it, see our tutorial on
how to install a graphics card and – if you’re starting from scratch,
how to build a gaming PC.
Author: Jim Martin, Executive Editor
Jim has been testing and reviewing products for over 20 years. His main beats include VPN services and antivirus. He also covers smart home tech, mesh Wi-Fi and electric bikes.
Nvidia GeForce GTX 1070 vs Zotac GTX 1080 Ti: What is the difference?
59points
Nvidia GeForce GTX 1070
67points
Zotac GTX 1080 Ti
Comparison winner
vs
54 facts in comparison
Nvidia GeForce GTX 1070
Zotac GTX 1080 Ti
Why is Nvidia GeForce GTX 1070 better than Zotac GTX 1080 Ti?
- 100W lower TDP?
150Wvs250W - 624MHz faster memory clock speed?
2000MHzvs1376MHz - 101MHz faster GPU turbo speed?
1683MHzvs1582MHz - Has Double Precision Floating Point (DPFP)?
- 1 more DVI outputs?
1vs0 - 2 more GPUs supported?
4vs2
Why is Zotac GTX 1080 Ti better than Nvidia GeForce GTX 1070?
- 5. 56 TFLOPS higher floating-point performance?
11.34 TFLOPSvs5.78 TFLOPS - 42.8 GPixel/s higher pixel rate?
139.2 GPixel/svs96.4 GPixel/s - 3008MHz higher effective memory clock speed?
11008MHzvs8000MHz - 173.7 GTexels/s higher texture rate?
354.4 GTexels/svs180.7 GTexels/s - 37.5% more VRAM?
11GBvs8GB - 228.4GB/s more memory bandwidth?
484.4GB/svs256GB/s - 96bit wider memory bus width?
352bitvs256bit - 1664 more shading units?
3584vs1920
Which are the most popular comparisons?
Nvidia GeForce GTX 1070
vs
Nvidia GeForce RTX 2060
Zotac GTX 1080 Ti
vs
Nvidia GeForce RTX 3060
Nvidia GeForce GTX 1070
vs
Nvidia GeForce RTX 3050 Laptop
Zotac GTX 1080 Ti
vs
Nvidia Geforce GTX 1660 Super
Nvidia GeForce GTX 1070
vs
Nvidia Geforce GTX 1660 Super
Zotac GTX 1080 Ti
vs
Nvidia GeForce RTX 3060 Ti
Nvidia GeForce GTX 1070
vs
AMD Radeon RX 580
Zotac GTX 1080 Ti
vs
AMD Radeon RX 6700 XT
Nvidia GeForce GTX 1070
vs
Nvidia GeForce GTX 1650 Ti Laptop
Zotac GTX 1080 Ti
vs
EVGA GeForce RTX 2060 Super SC Ultra
Nvidia GeForce GTX 1070
vs
Manli GeForce GTX 1650
Zotac GTX 1080 Ti
vs
Nvidia GeForce RTX 2060 Super
Nvidia GeForce GTX 1070
vs
Nvidia GeForce RTX 3050 Ti Laptop
Zotac GTX 1080 Ti
vs
Nvidia GeForce RTX 3070 Laptop
Nvidia GeForce GTX 1070
vs
Nvidia GeForce RTX 3050
Zotac GTX 1080 Ti
vs
Nvidia GeForce RTX 3070
Nvidia GeForce GTX 1070
vs
Nvidia GeForce GTX 1660
Zotac GTX 1080 Ti
vs
Nvidia GeForce RTX 3070 Ti
Nvidia GeForce GTX 1070
vs
Nvidia GeForce GTX 1660 Ti
Zotac GTX 1080 Ti
vs
Nvidia GeForce GTX 1650
Price comparison
User reviews
Overall Rating
Nvidia GeForce GTX 1070
3 User reviews
Nvidia GeForce GTX 1070
9. 3/10
3 User reviews
Zotac GTX 1080 Ti
0 User reviews
Zotac GTX 1080 Ti
0.0/10
0 User reviews
Features
Value for money
9.3/10
3 votes
No reviews yet
Gaming
9.0/10
3 votes
No reviews yet
Performance
9.7/10
3 votes
No reviews yet
Fan noise
9.7/10
3 votes
No reviews yet
Reliability
10.0/10
3 votes
No reviews yet
Performance
1.GPU clock speed
1506MHz
1481MHz
The graphics processing unit (GPU) has a higher clock speed.
2.GPU turbo
1683MHz
1582MHz
When the GPU is running below its limitations, it can boost to a higher clock speed in order to give increased performance.
3.pixel rate
96.4 GPixel/s
139. 2 GPixel/s
The number of pixels that can be rendered to the screen every second.
4.floating-point performance
5.78 TFLOPS
11.34 TFLOPS
Floating-point performance is a measurement of the raw processing power of the GPU.
5.texture rate
180.7 GTexels/s
354.4 GTexels/s
The number of textured pixels that can be rendered to the screen every second.
6.GPU memory speed
2000MHz
1376MHz
The memory clock speed is one aspect that determines the memory bandwidth.
7.shading units
Shading units (or stream processors) are small processors within the graphics card that are responsible for processing different aspects of the image.
8.texture mapping units (TMUs)
TMUs take textures and map them to the geometry of a 3D scene. More TMUs will typically mean that texture information is processed faster.
9.render output units (ROPs)
The ROPs are responsible for some of the final steps of the rendering process, writing the final pixel data to memory and carrying out other tasks such as anti-aliasing to improve the look of graphics.
Memory
1.effective memory speed
8000MHz
11008MHz
The effective memory clock speed is calculated from the size and data rate of the memory. Higher clock speeds can give increased performance in games and other apps.
2.maximum memory bandwidth
256GB/s
484.4GB/s
This is the maximum rate that data can be read from or stored into memory.
3.VRAM
VRAM (video RAM) is the dedicated memory of a graphics card. More VRAM generally allows you to run games at higher settings, especially for things like texture resolution.
4.memory bus width
256bit
352bit
A wider bus width means that it can carry more data per cycle. It is an important factor of memory performance, and therefore the general performance of the graphics card.
5.version of GDDR memory
Newer versions of GDDR memory offer improvements such as higher transfer rates that give increased performance.
6.Supports ECC memory
✖Nvidia GeForce GTX 1070
✖Zotac GTX 1080 Ti
Error-correcting code memory can detect and correct data corruption. It is used when is it essential to avoid corruption, such as scientific computing or when running a server.
Features
1.DirectX version
DirectX is used in games, with newer versions supporting better graphics.
2.OpenGL version
OpenGL is used in games, with newer versions supporting better graphics.
3.OpenCL version
Some apps use OpenCL to apply the power of the graphics processing unit (GPU) for non-graphical computing. Newer versions introduce more functionality and better performance.
4.Supports multi-display technology
✔Nvidia GeForce GTX 1070
✔Zotac GTX 1080 Ti
The graphics card supports multi-display technology. This allows you to configure multiple monitors in order to create a more immersive gaming experience, such as having a wider field of view.
5.load GPU temperature
Unknown. Help us by suggesting a value. (Nvidia GeForce GTX 1070)
A lower load temperature means that the card produces less heat and its cooling system performs better.
6.supports ray tracing
✔Nvidia GeForce GTX 1070
✔Zotac GTX 1080 Ti
Ray tracing is an advanced light rendering technique that provides more realistic lighting, shadows, and reflections in games.
7.Supports 3D
✔Nvidia GeForce GTX 1070
✔Zotac GTX 1080 Ti
Allows you to view in 3D (if you have a 3D display and glasses).
8.supports DLSS
✖Nvidia GeForce GTX 1070
✖Zotac GTX 1080 Ti
DLSS (Deep Learning Super Sampling) is an upscaling technology powered by AI. It allows the graphics card to render games at a lower resolution and upscale them to a higher resolution with near-native visual quality and increased performance. DLSS is only available on select games.
9.PassMark (G3D) result
Unknown. Help us by suggesting a value. (Nvidia GeForce GTX 1070)
This benchmark measures the graphics performance of a video card. Source: PassMark.
Ports
1.has an HDMI output
✔Nvidia GeForce GTX 1070
✔Zotac GTX 1080 Ti
Devices with a HDMI or mini HDMI port can transfer high definition video and audio to a display.
2.HDMI ports
More HDMI ports mean that you can simultaneously connect numerous devices, such as video game consoles and set-top boxes.
3.HDMI version
HDMI 2.0
HDMI 2.0
Newer versions of HDMI support higher bandwidth, which allows for higher resolutions and frame rates.
4.DisplayPort outputs
Allows you to connect to a display using DisplayPort.
5.DVI outputs
Allows you to connect to a display using DVI.
6.mini DisplayPort outputs
Allows you to connect to a display using mini-DisplayPort.
Price comparison
Cancel
Which are the best graphics cards?
Asus ROG Strix GeForce GTX 1070 vs MSI GTX 1080 Ti Gaming X: What is the difference?
58points
61points
Asus ROG Strix GeForce GTX 1070
71points
68points
MSI GTX 1080 Ti Gaming X
w/ USB Type-C
Comparison winner
Cost-effectiveness winner
vs
54 facts in comparison
Asus ROG Strix GeForce GTX 1070
MSI GTX 1080 Ti Gaming X
Why is Asus ROG Strix GeForce GTX 1070 better than MSI GTX 1080 Ti Gaming X?
- 113MHz faster GPU clock speed?
1657MHzvs1544MHz - 100W lower TDP?
150Wvs250W - 626MHz faster memory clock speed?
2002MHzvs1376MHz - 203MHz faster GPU turbo speed?
1860MHzvs1657MHz - 2 more GPUs supported?
4vs2 - 39. 29% cheaper?
499.00 €vs822.00 €
Why is MSI GTX 1080 Ti Gaming X better than Asus ROG Strix GeForce GTX 1070?
- 5.41 TFLOPS higher floating-point performance?
11.88 TFLOPSvs6.46 TFLOPS - 38.1 GPixel/s higher pixel rate?
145.8 GPixel/svs107.7 GPixel/s - 3000MHz higher effective memory clock speed?
11008MHzvs8008MHz - 169.2 GTexels/s higher texture rate?
371.2 GTexels/svs202 GTexels/s - 37.5% more VRAM?
11GBvs8GB - 228.1GB/s more memory bandwidth?
484.4GB/svs256.3GB/s - 96bit wider memory bus width?
352bitvs256bit - 1664 more shading units?
3584vs1920
Which are the most popular comparisons?
Asus ROG Strix GeForce GTX 1070
vs
Gigabyte GeForce GTX 1070 G1 Gaming
MSI GTX 1080 Ti Gaming X
vs
Asus ROG Strix GeForce GTX 1080 Ti OC
Asus ROG Strix GeForce GTX 1070
vs
MSI Radeon RX 570 Armor OC 8GB
MSI GTX 1080 Ti Gaming X
vs
EVGA GeForce GTX 1080 Ti Gaming
Asus ROG Strix GeForce GTX 1070
vs
Zotac GeForce GTX 1070 Ti Mini
MSI GTX 1080 Ti Gaming X
vs
MSI GeForce GTX 1080 Gaming X
Asus ROG Strix GeForce GTX 1070
vs
Gigabyte GeForce RTX 2060 Super WindForce OC
MSI GTX 1080 Ti Gaming X
vs
MSI GeForce GTX 1080 Founders Edition
Asus ROG Strix GeForce GTX 1070
vs
Asus ROG Strix GTX 1070 Ti Gaming Advanced
MSI GTX 1080 Ti Gaming X
vs
MSI GTX 1080 Ti Gaming X TRIO
Asus ROG Strix GeForce GTX 1070
vs
Asus ROG Strix GeForce GTX 1080
MSI GTX 1080 Ti Gaming X
vs
MSI GeForce RTX 2080 Gaming X Trio
Asus ROG Strix GeForce GTX 1070
vs
Nvidia GeForce RTX 2060
MSI GTX 1080 Ti Gaming X
vs
MSI GTX 1080 Ti Gaming X w/ USB Type-C
Asus ROG Strix GeForce GTX 1070
vs
Sapphire Nitro+ Radeon RX 580 8GB
MSI GTX 1080 Ti Gaming X
vs
Asus Turbo GTX 1080 Ti
Asus ROG Strix GeForce GTX 1070
vs
Asus ROG Strix Radeon RX 580 Gaming
MSI GTX 1080 Ti Gaming X
vs
EVGA GeForce GTX 1080 Ti FTW3 w/ iCX Cooler
Asus ROG Strix GeForce GTX 1070
vs
Nvidia GeForce GTX 1660 Ti
MSI GTX 1080 Ti Gaming X
vs
Palit GTX 1080 Ti GameRock Premium
Price comparison
Cheap alternatives
User reviews
Performance
1. GPU clock speed
1657MHz
1544MHz
The graphics processing unit (GPU) has a higher clock speed.
2.GPU turbo
1860MHz
1657MHz
When the GPU is running below its limitations, it can boost to a higher clock speed in order to give increased performance.
3.pixel rate
107.7 GPixel/s
145.8 GPixel/s
The number of pixels that can be rendered to the screen every second.
4.floating-point performance
6.46 TFLOPS
11.88 TFLOPS
Floating-point performance is a measurement of the raw processing power of the GPU.
5.texture rate
202 GTexels/s
371.2 GTexels/s
The number of textured pixels that can be rendered to the screen every second.
6.GPU memory speed
2002MHz
1376MHz
The memory clock speed is one aspect that determines the memory bandwidth.
7.shading units
Shading units (or stream processors) are small processors within the graphics card that are responsible for processing different aspects of the image.
8.texture mapping units (TMUs)
TMUs take textures and map them to the geometry of a 3D scene. More TMUs will typically mean that texture information is processed faster.
9.render output units (ROPs)
The ROPs are responsible for some of the final steps of the rendering process, writing the final pixel data to memory and carrying out other tasks such as anti-aliasing to improve the look of graphics.
Memory
1.effective memory speed
8008MHz
11008MHz
The effective memory clock speed is calculated from the size and data rate of the memory. Higher clock speeds can give increased performance in games and other apps.
2. maximum memory bandwidth
256.3GB/s
484.4GB/s
This is the maximum rate that data can be read from or stored into memory.
3.VRAM
VRAM (video RAM) is the dedicated memory of a graphics card. More VRAM generally allows you to run games at higher settings, especially for things like texture resolution.
4.memory bus width
256bit
352bit
A wider bus width means that it can carry more data per cycle. It is an important factor of memory performance, and therefore the general performance of the graphics card.
5.version of GDDR memory
Newer versions of GDDR memory offer improvements such as higher transfer rates that give increased performance.
6.Supports ECC memory
✖Asus ROG Strix GeForce GTX 1070
✖MSI GTX 1080 Ti Gaming X
Error-correcting code memory can detect and correct data corruption. It is used when is it essential to avoid corruption, such as scientific computing or when running a server.
Features
1.DirectX version
DirectX is used in games, with newer versions supporting better graphics.
2.OpenGL version
OpenGL is used in games, with newer versions supporting better graphics.
3.OpenCL version
Some apps use OpenCL to apply the power of the graphics processing unit (GPU) for non-graphical computing. Newer versions introduce more functionality and better performance.
4.Supports multi-display technology
✔Asus ROG Strix GeForce GTX 1070
✔MSI GTX 1080 Ti Gaming X
The graphics card supports multi-display technology. This allows you to configure multiple monitors in order to create a more immersive gaming experience, such as having a wider field of view.
5. load GPU temperature
Unknown. Help us by suggesting a value. (Asus ROG Strix GeForce GTX 1070)
A lower load temperature means that the card produces less heat and its cooling system performs better.
6.supports ray tracing
✔Asus ROG Strix GeForce GTX 1070
✔MSI GTX 1080 Ti Gaming X
Ray tracing is an advanced light rendering technique that provides more realistic lighting, shadows, and reflections in games.
7.Supports 3D
✔Asus ROG Strix GeForce GTX 1070
✔MSI GTX 1080 Ti Gaming X
Allows you to view in 3D (if you have a 3D display and glasses).
8.supports DLSS
✖Asus ROG Strix GeForce GTX 1070
✖MSI GTX 1080 Ti Gaming X
DLSS (Deep Learning Super Sampling) is an upscaling technology powered by AI. It allows the graphics card to render games at a lower resolution and upscale them to a higher resolution with near-native visual quality and increased performance. DLSS is only available on select games.
9.PassMark (G3D) result
Unknown. Help us by suggesting a value. (Asus ROG Strix GeForce GTX 1070)
This benchmark measures the graphics performance of a video card. Source: PassMark.
Ports
1.has an HDMI output
✔Asus ROG Strix GeForce GTX 1070
✔MSI GTX 1080 Ti Gaming X
Devices with a HDMI or mini HDMI port can transfer high definition video and audio to a display.
2.HDMI ports
More HDMI ports mean that you can simultaneously connect numerous devices, such as video game consoles and set-top boxes.
3.HDMI version
HDMI 2.0
HDMI 2.0
Newer versions of HDMI support higher bandwidth, which allows for higher resolutions and frame rates.
4.DisplayPort outputs
Allows you to connect to a display using DisplayPort.
5.DVI outputs
Allows you to connect to a display using DVI.
6.mini DisplayPort outputs
Allows you to connect to a display using mini-DisplayPort.
Price comparison
Cancel
Which are the best graphics cards?
0024 1607MHz vs 1480MHz
180W vs 220W
2002MHz vs 1376MHz
1683MHz vs 1582MHz
1 vs 0
Why is Nvidia GeForce GTX 1080 Ti better than Nvidia GeForce GTX 1070 Ti?
- 2.41 TFLOPS higher than FLOPS?
10.6 TFLOPS vs 8.19 TFLOPS - 22.5 GPixel/s higher pixel rate?
130.2 GPixel/s vs 107.7 GPixel/s - 3000MHz higher effective clock speed?
11008MHz vs 8008MHz - 76. 2 GTexels/s higher number of textured pixels?
332 GTexels/s vs 255.8 GTexels/s - 37.5% more VRAM?
11GB vs 8GB - 227.7GB/s more memory bandwidth?
484GB/s vs 256.3GB/s - 96bit wider memory bus?
352bit vs 256bit - 1152 more stream processors?
3584 vs 2432
Which comparisons are the most popular?
Nvidia GeForce GTX 1070 Ti
vs
Nvidia GeForce RTX 2060
Nvidia GeForce GTX 1080 Ti
vs
Nvidia GeForce RTX 3060
Nvidia GeForce GTX 1070 Ti
vs
Nvidia GeForce RTX 3050 Laptop
Nvidia GeForce GTX 1080 Ti
vs
Nvidia GeForce RTX 3060 Ti
Nvidia GeForce GTX 1070 Ti
vs
Nvidia Geforce GTX 1660 Super
Nvidia GeForce GTX 1080 Ti
vs
Nvidia GeForce RTX 3050 Laptop
Nvidia GeForce GTX 1080 Ti 940003
Nvidia GeForce RTX 3050 Ti Laptop
Nvidia GeForce GTX 1080 Ti
vs
Nvidia GeForce GTX 1660 Ti
Nvidia GeForce GTX 1070 Ti
vs
Nvidia GeForce RTX 3060 Ti
Nvidia GeForce GTX 1080 Ti
VS
NVIDIA GEFORCE RTX 2060
NVIDIA GEFORCE GTX 1070 TI
VS
Manli GeForce GTX 1650
NVIDIA GTX 1080 TI
9000 9000 SUPER NVIDIRA GTOR SUPOR NVIDIA GTOR SUPOR0003
Nvidia GeForce GTX 1070 Ti
vs
Nvidia GeForce GTX 1070
Nvidia GeForce GTX 1080 Ti
vs
Nvidia GeForce RTX 3080
Nvidia GeForce GTX 1070 Ti
vs
Nvidia GeForce GTX 1660 Ti
AMD Radeon RX 580
Nvidia GeForce GTX 1070 Ti0004 NVIDIA GeForce GTX 1080 TI
10. 0 /10
1 Reviews Users
Functions
Cost Reviews
Reviews are not
/10
9000 Reviews are not yet
9.0 /10
1 Votes
performance
reviews yet there are no
10.0 /10
9000 9,0003 9000 9000
004 1 Votes
Fan noise
Reviews not yet
10.0 /10
1 VOTES
Reliability
Reviews yet not
10.0 /10 9000
1.GPU clock speed
1607MHz
1480MHz
The graphics processing unit (GPU) has a higher clock speed.
2.Turbo GPU
1683MHz
1582MHz
When the GPU is running below its limits, it can jump to a higher clock speed to increase performance.
3.pixel rate
107.7 GPixel/s
130.2 GPixel/s
The number of pixels that can be displayed on the screen every second.
4.flops
8.19 TFLOPS
10.6 TFLOPS
FLOPS is a measurement of GPU processing power.
5.texture size
255.8 GTexels/s
332 GTexels/s
The number of textured pixels that can be displayed on the screen every second.
6.GPU memory speed
2002MHz
1376MHz
Memory speed is one aspect that determines memory bandwidth.
7.shading patterns
Shading units (or stream processors) are small processors in a video card that are responsible for processing various aspects of an image.
8.textured units (TMUs)
TMUs accept textured units and bind them to the geometric layout of the 3D scene. More TMUs generally means texture information is processed faster.
9 ROPs
ROPs are responsible for some of the final steps of the rendering process, such as writing the final pixel data to memory and for performing other tasks such as anti-aliasing to improve the appearance of graphics.
Memory
1.memory effective speed
8008MHz
11008MHz
The effective memory clock frequency is calculated from the size and data transfer rate of the memory. A higher clock speed can give better performance in games and other applications.
2.max memory bandwidth
256.3GB/s
484GB/s
This is the maximum rate at which data can be read from or stored in memory.
3.VRAM
VRAM (video RAM) is the dedicated memory of the graphics card. More VRAM usually allows you to run games at higher settings, especially for things like texture resolution.
4.memory bus width
256bit
352bit
Wider memory bus means it can carry more data per cycle. This is an important factor in memory performance, and therefore the overall performance of the graphics card.
5. versions of GDDR memory
Later versions of GDDR memory offer improvements such as higher data transfer rates, which improve performance.
6. Supports memory debug code
✖Nvidia GeForce GTX 1070 Ti
✖Nvidia GeForce GTX 1080 Ti
Memory debug code can detect and fix data corruption. It is used when necessary to avoid distortion, such as in scientific computing or when starting a server.
Functions
1.DirectX version
DirectX is used in games with a new version that supports better graphics.
2nd version of OpenGL
The newer version of OpenGL, the better graphics quality in games.
OpenCL version 3.
Some applications use OpenCL to use the power of the graphics processing unit (GPU) for non-graphical computing. Newer versions are more functional and better quality.
4. Supports multi-monitor technology
✔Nvidia GeForce GTX 1070 Ti
✔Nvidia GeForce GTX 1080 Ti
The video card has the ability to connect multiple screens. This allows you to set up multiple monitors at the same time to create a more immersive gaming experience, such as a wider field of view.
5. GPU temperature at boot
Unknown. Help us offer a price. (Nvidia GeForce GTX 1080 Ti)
Lower boot temperature means the card generates less heat and the cooling system works better.
6.supports ray tracing
✔Nvidia GeForce GTX 1070 Ti
✖Nvidia GeForce GTX 1080 Ti
Ray tracing is an advanced light rendering technique that provides more realistic lighting, shadows and reflections in games.
7. Supports 3D
✔Nvidia GeForce GTX 1070 Ti
✔Nvidia GeForce GTX 1080 Ti
Allows you to view in 3D (if you have a 3D screen and glasses).
8.supports DLSS
✖Nvidia GeForce GTX 1070 Ti
✖Nvidia GeForce GTX 1080 Ti
DLSS (Deep Learning Super Sampling) is an AI based scaling technology. This allows the graphics card to render games at lower resolutions and upscale them to higher resolutions with near-native visual quality and improved performance. DLSS is only available in some games.
9. PassMark result (G3D)
Unknown. Help us offer a price. (Nvidia GeForce GTX 1070 Ti)
Unknown. Help us offer a price. (Nvidia GeForce GTX 1080 Ti)
This test measures the graphics performance of a graphics card. Source: Pass Mark.
Ports
1.has HDMI output
✔Nvidia GeForce GTX 1070 Ti
✔Nvidia GeForce GTX 1080 Ti
Devices with HDMI or mini HDMI ports can stream HD video and audio to an attached display.
2. HDMI connectors
More HDMI connectors allow you to connect multiple devices at the same time, such as game consoles and TVs.
HDMI 3.Version
HDMI 2.0
HDMI 2.0
New HDMI versions support higher bandwidth for higher resolutions and frame rates.
4. DisplayPort outputs
Allows connection to a display using DisplayPort.
5.DVI outputs
Allows connection to a display using DVI.
Mini DisplayPort 6.outs
Allows connection to a display using Mini DisplayPort.
- 100W below TDP?
150W vs 250W - 624MHz faster memory speed?
2000MHz vs 1376MHz - Has DPFP?
- 2 supports more GPUs?
4 vs 2 - 33mm narrower?
267mm vs 300mm - 37mm lower? Why is Zotac GeForce GTX 1080 Ti ArcticStorm better than Nvidia GeForce GTX 1070?
- 5. 83 TFLOPS over FLOPS?
11.61 TFLOPS vs 5.78 TFLOPS - 46.2 GPixel/s higher pixel rate?
142.6 GPixel/s vs 96.4 GPixel/s - 3008MHz higher effective clock speed?
11008MHz vs 8000MHz - 182.2 GTexels/s higher number of textured pixels?
362.9 GTexels/s vs 180.7 GTexels/s - 37.5% more VRAM?
11GB vs 8GB - 228.4GB/s more memory bandwidth?
484.4GB/s vs 256GB/s - 96bit wider memory bus?
352bit vs 256bit - 1664 more stream processors?
3584 vs 1920
Which comparisons are the most popular?
Nvidia GeForce GTX 1070
vs
Nvidia GeForce RTX 2060
Zotac GeForce GTX 1080 Ti ArcticStorm
vs
XFX HD 6950 XXX 1GB
Nvidia GeForce GTX 1070
vs
Nvidia GeForce RTX 3050 Laptop
Zotac GeForce GTX 1080 Ti ArcticStorm
vs
Nvidia Tesla C2050
Nvidia GeForce GTX 1070
vs
Nvidia Geforce GTX 1660 Super
Zotac GeForce GTX 1080 Ti ArcticStorm
0003
Zotac GeForce GTX 1080 Ti ArcticStorm
vs
AMD Radeon RX 570
Nvidia GeForce GTX 1070
vs
Nvidia GeForce GTX 1650 Ti Laptop
Zotac GeForce GTX 1080 Ti ArcticStorm
vs
AMD Radeon RX 470
NVIDIA GeForce GTX 1070
VS
Manli GeForce GTX 1650
ZOTAC GEFORCE GTX 1080 TI Arcticstorm
NVIDIA GEFORCE GTX GTX GTX GTX GTX0003
vs
Nvidia GeForce RTX 3050 Ti Laptop
Zotac GeForce GTX 1080 Ti ArcticStorm
vs
Nvidia Quadro GP100
Nvidia GeForce GTX 1070
vs
Nvidia GeForce RTX 3050
Zotac GeForce GTX 1080 Ti ArcticStorm
vs
Nvidia Quadro P4000
Nvidia GeForce GTX 1070
vs
Nvidia GeForce GTX 1660
Zotac GeForce GTX 1080 Ti ArcticStorm
0003
9. 7 /10
3 VOTES
Reviews not yet
RIGHT TALKER
9.7 /10
3 VOTES
Reviews yet not
/
3 votes
No reviews yet
Performance
2.turbo GPU
1683MHz
1620MHz
When the GPU is running below its limits, it can jump to a higher clock speed to increase performance.
3.pixel rate
96.4 GPixel/s
142.6 GPixel/s
The number of pixels that can be displayed on the screen every second.
4.flops
5.78 TFLOPS
11.61 TFLOPS
FLOPS is a measure of GPU processing power.
5.texture size
180.7 GTexels/s
362.9 GTexels/s
Number of textured pixels that can be displayed on the screen every second.
6.GPU memory speed
2000MHz
1376MHz
Memory speed is one aspect that determines memory bandwidth.
7.shading patterns
Shading units (or stream processors) are small processors in a video card that are responsible for processing various aspects of an image.
8.textured units (TMUs)
TMUs accept textured units and bind them to the geometric layout of the 3D scene. More TMUs generally means texture information is processed faster.
9 ROPs
ROPs are responsible for some of the final steps of the rendering process, such as writing the final pixel data to memory and for performing other tasks such as anti-aliasing to improve the appearance of graphics.
Memory
1.memory effective speed
8000MHz
11008MHz
The effective memory clock frequency is calculated from the size and data transfer rate of the memory. A higher clock speed can give better performance in games and other applications.
2.max memory bandwidth
256GB/s
484.4GB/s
This is the maximum rate at which data can be read from or stored in memory.
3.VRAM
VRAM (video RAM) is the dedicated memory of the graphics card. More VRAM usually allows you to run games at higher settings, especially for things like texture resolution.
4.memory bus width
256bit
352bit
Wider memory bus means it can carry more data per cycle. This is an important factor in memory performance, and therefore the overall performance of the graphics card.
5.versions of GDDR memory
Later versions of GDDR memory offer improvements such as higher data transfer rates, which improve performance.
6. Supports memory debug code
✖Nvidia GeForce GTX 1070
✖Zotac GeForce GTX 1080 Ti ArcticStorm
Memory debug code can detect and fix data corruption. It is used when necessary to avoid distortion, such as in scientific computing or when starting a server.
Functions
1.DirectX version
DirectX is used in games with a new version that supports better graphics.
2nd version of OpenGL
The newer version of OpenGL, the better graphics quality in games.
OpenCL version 3.
Some applications use OpenCL to use the power of the graphics processing unit (GPU) for non-graphical computing. Newer versions are more functional and better quality.
4. Supports multi-monitor technology
✔Nvidia GeForce GTX 1070
✔Zotac GeForce GTX 1080 Ti ArcticStorm
The video card has the ability to connect multiple screens. This allows you to set up multiple monitors at the same time to create a more immersive gaming experience, such as a wider field of view.
5. GPU temperature at boot
Unknown. Help us offer a price. (Nvidia GeForce GTX 1070)
Lower boot temperature means the card generates less heat and the cooling system works better.
6.supports ray tracing
✔Nvidia GeForce GTX 1070
✔Zotac GeForce GTX 1080 Ti ArcticStorm
Ray tracing is an advanced light rendering technique that provides more realistic lighting, shadows and reflections in games.
7. Supports 3D
✔Nvidia GeForce GTX 1070
✔Zotac GeForce GTX 1080 Ti ArcticStorm
Allows you to view in 3D (if you have a 3D screen and glasses).
8.supports DLSS
✖Nvidia GeForce GTX 1070
✖Zotac GeForce GTX 1080 Ti ArcticStorm
DLSS (Deep Learning Super Sampling) is an AI based scaling technology. This allows the graphics card to render games at lower resolutions and upscale them to higher resolutions with near-native visual quality and improved performance. DLSS is only available in some games.
9. PassMark result (G3D)
Unknown. Help us offer a price. (Nvidia GeForce GTX 1070)
This test measures the graphics performance of a graphics card. Source: Pass Mark.
Ports
1.has HDMI output
✔Nvidia GeForce GTX 1070
✔Zotac GeForce GTX 1080 Ti ArcticStorm
Devices with HDMI or mini HDMI ports can stream video and audio to an attached HD display.
2.HDMI connectors
More HDMI connectors allow you to connect multiple devices at the same time, such as game consoles and TVs.
HDMI 3.Version
HDMI 2.0
HDMI 2.0
New HDMI versions support higher bandwidth for higher resolutions and frame rates.
4. DisplayPort outputs
Allows connection to a display using DisplayPort.
5. DVI outputs
Allows connection to a display using DVI.
Mini DisplayPort 6.outs
Allows connection to a display using Mini DisplayPort.
Price match
Cancel
Which graphic cards are better?
Comparison NVIDIA GeForce GTX 1080 Ti vs NVIDIA GeForce GTX 1070 SLI which is better?
General information Price-quality ratio
The sum of all the advantages of the device divided by its price. The more%, the better the quality per unit price in comparison with all analogues.
0.248 %
n/a Architecture
Pascal Pascal Codename
GP102 Pascal GP104 SLI Type
Desktop Desktop Release price
699 $ n/a Number of shaders
3584 3840 256 (7. 1%) better than
Core clock
1481MHz 1506 MHz 25 MHz (1.7%) better than
Boost frequency
1582 MHz 1683 MHz 101 MHz (6.4%) better than
Number of transistors
11.800 million 14400 million Process
16 nm 16 nm Interface
PCIe 3.0 x16 n/a Power Demand (TDP)
The calculated heat output shows the average heat dissipation in load operation,
the larger the value, the more the requirements for cooling and power consumption increase.250W -50 W (-16.7%) better than
300W Length
26. 7 cm n/a Additional power connectors
1x 6-pin + 1x 8-pin n/a G-SYNC Ready
NVIDIA G-SYNC technology delivers a smooth gaming experience with variable refresh rates and the elimination of visual artifacts.
Multi Monitor
n/a + SLI support
+ + 3D Vision
+ + GPU Boost
+ + GeForce Experience
n/a + VR Ready
Technology from NVIDIA that gives manufacturers access to Multi res Shading, Context Priority, and GPU Direct virtual reality technologies.
n/a + Vulkan
NVIDIA’s Vulkan technology allows developers to gain low-level access to the GPU to optimize graphics commands (better than OpenGL and Direct3D APIs).
It is an open, free, cross-platform standard available for all platforms.+ + CUDA
The CUDA architecture enables applications that are optimized for
parallel computing. For example, for the development and design of neural networks.Surround
n/a + Adaptive Vertical Sync
n/a + Multi-Projection
NVIDIA’s Multi-Projection technology improves graphics card performance when building virtual worlds. Images for the left and right eyes are calculated simultaneously.
n/a + Maximum temperature
91 °C n/a Recommended Power Supply
600W n/a Multi-monitor support
1 n/a Ansel
Virtual Reality
+ n/a Decred / DCR (Decred)
4.6 Gh/s n/a Siacoin / SC (Sia)
2.96 Gh/s n/a Zcash / ZEC (Equihash)
1 Sol/s n/a Video connectors
1x HDMI, 3x DisplayPort n/a DirectX
12 (12_1) DirectX 12_1 Floating point performance
11. 340 gflops n/a Ethereum / ETH (DaggerHashimoto)
35 Mh/s n/a Memory Memory type
GDDR5X GDDR5 Maximum memory
Large video memory allows you to run demanding games with lots of textures,
use high resolution monitors, provide more opportunities for cryptocurrency mining.11 GB 3 GB (37.5%) better than
8 GB Memory bus width
The wider the video memory bus, the more data is transferred to the GPU per unit of time and the better performance in demanding games.
352 bit 96 bit (37.5%) better than
256 bit Shared memory
— — Memory frequency
A high memory frequency has a positive effect on the speed of a video card with a large amount of data.
11008 MHz At 3008 MHz (37.6%) better than
8000 MHz Memory bandwidth
The higher the data transfer bandwidth, the more effective amount of RAM the PC can use.
Average: 938 MHz
1607MHz
max 2457
Average: 938 MHz
GPU memory frequency
This is an important aspect calculating memory bandwidth
1376MHz
max 16000
Average: 1326.6 MHz
2002MHz
max 16000
Average: 1326.6 MHz
FLOPS
The measurement of processing power of a processor is called FLOPS.
11.3TFLOPS
max 1142.32
Average: 92.5 TFLOPS
7.9TFLOPS
max 1142.32
Average: 92.5 TFLOPS
Turbo GPU
If the GPU speed drops below its limit, it can switch to a high clock speed to improve performance.
Show all1582MHz
max 2903
Average: 1375.8 MHz
1683MHz
max 2903
Average: 1375.8 MHz
Texture size
A certain number of textured pixels are displayed on the screen every second.
Show all332 GTexels/s
max 756. 8
Average: 145.4 GTexels/s
255.8 GTexels/s
max 756.8
Average: 145.4 GTexels/s
Architecture name
Pascal
Pascal
Graphic processor name
GP102
GP104
DECARITEMENT FIRE 9,0003 which the device stores or reads information.
484.4GB/s
max 2656
Average: 198.3 GB/s
256.3GB/s
max 2656
Average: 198.3 GB/s
Effective memory speed
The effective memory clock speed is calculated from the size and information transfer rate of the memory. The performance of the device in applications depends on the clock frequency. The higher it is, the better.
Show all11008MHz
max 19500
Average: 6984.5 MHz
8008 MHz
max 19500
Average: 6984.5 MHz
RAM
11GB
max 128
Average: 4.6 GB
8GB
max 128
Average: 4.6 GB
GDDR Memory Versions
Latest GDDR memory versions provide high data transfer rates for improved overall performance
Show all5
Average: 4.5
5
Average: 4. 5
Memory bus width
A wide memory bus means that it can transfer more information in one cycle. This property affects the performance of the memory as well as the overall performance of the device’s graphics card.
Show all352bit
max 8192
Average: 290.1bit
256bit
max 8192
Average: 290.1bit
Date of Release
2017-02-28 00:00:00
2017-11-02 00:00
Heating (TDP)
Thermal Requirements (TDP)-the maximum possible amount energy dissipated by the cooling system. The lower the TDP, the less power will be consumed.
Show all250W
Average: 140. 4W
180W
Average: 140.4W
Process technology
The small size of the semiconductor means it is a new generation chip.
16 nm
Average: 47.5 nm
16 nm
Average: 47.5 nm
Number of transistors
The higher their number, the more processor power it indicates
11800 million
max 80000
Average: 5043 million
7200 million
max 80000
Average: 5043 million
PCIe version
Provides considerable speed for an expansion card used to connect a computer to peripherals. The updated versions have impressive throughput and provide high performance.
Show all3
Mean: 2.8
3
Mean: 2.8
Width
266.7mm
max 421.7
Average: 242.6mm
266.7mm
max 421.7
Average: 242.6mm
Height
111.2mm
max 180
Average: 119.1mm
111.2mm
max 180
Average: 119.1mm
Purpose
Desktop
Desktop
DirectX
Used in demanding games, providing improved graphics
12
max 12. 2
Average: 11.1
12
max 12.2
Average: 11.1
OpenCL version
Used by some applications to enable GPU power for non-graphical calculations. The newer the version, the more functional it will be
Show all3
max 4.6
Average: 1.7
3
max 4.6
Average: 1.7
opengl version
Later versions provide better game graphics
4.6
max 4.6
Average: 4
4.6
max 4. 6
Average: 4
Shader model version
6.4
max 6.6
Average: 5.5
6.4
max 6.6
Average: 5.5
version Vulkan
1.3
1.3
version CUDA
6.1
6.1
HDMI Output
9000 They can transmit video and audio to the display.
Show allYes
Yes
HDMI version
The latest version provides a wide signal transmission channel due to the increased number of audio channels, frames per second, etc.
Show all2
max 2.1
Average: 2
2
max 2. 1
Average: 2
DisplayPort
Allows connection to a display using DisplayPort
3
Average: 2
3
Average: 2
Number of HDMI connectors
The more there are, the more devices can be connected at the same time (for example, game/TV type consoles)
Show allone
Average: 1.1
one
Average: 1.1
HDMI
Yes
Yes
Passmark score
17693
max 29325
Average: 7628. 6
14021
max 29325
Average: 7628.6
3DMark Cloud Gate GPU test score
139640
max 1
Average: 80042.3
86398
max 1
Average: 80042.3
3DMark Fire Strike Score
19224
max 38276
Average: 12463
14760
max 38276
Average: 12463
3DMark Fire Strike Graphics test score
27013
max 49575
Average: 11859. 1
18037
max 49575
Average: 11859.one
3DMark 11 Performance GPU score
36919
max 57937
Average: 18799.9
26953
max 57937
Average: 18799.9
3DMark Ice Storm GPU score
386800
max 533357
Average: 372425.7
433263
max 533357
Average: 372425.7
SPECviewperf 12 test score — Solidworks
67
max 202
Average: 62. 4
max 202
Average: 62.4
SPECviewperf 12 test evaluation — specvp12 sw-03
67
max 202
Average: 64
max 202
Average: 64
SPECviewperf 12 test evaluation — Siemens NX
ten
max 212
Average: 14
max 212
Average: 14
SPECviewperf 12 test score — specvp12 showcase-01
146
max 232
Average: 121.3
max 232
Average: 121.3
SPECviewperf 12 test score — Showcase
146
max 175
Average: 108. 4
max 175
Average: 108.4
SPECviewperf 12 test score — Medical
57
max 107
Average: 39.6
max 107
Average: 39.6
SPECviewperf 12 test score — specvp12 mediacal-01
57
max 107
Average: 39
max 107
Average: 39
SPECviewperf 12 test score — Maya
172
max 177
Average: 129.8
max 177
Average: 129.8
SPECviewperf 12 test score — specvp12 maya-04
172
max 180
Average: 132. 8
max 180
Average: 132.8
SPECviewperf 12 test score — Creo
59
max 153
Average: 49.5
max 153
Average: 49.5
SPECviewperf 12 test score — specvp12 creo-01
59
max 153
Average: 52.5
max 153
Average: 52.5
SPECviewperf 12 test score — specvp12 catia-04
103
max 189
Average: 91.5
max 189
Average: 91.5
SPECviewperf 12 evaluation — Catia
103
max 189
Average: 88. 6
max 189
Average: 88.6
SPECviewperf 12 test score — specvp12 3dsmax-05
145
max 316
Average: 189.5
max 316
Average: 189.5
SPECviewperf 12 test score — 3ds Max
143
max 269
Average: 169.8
max 269
Average: 169.8
GIGABYTE GeForce GTX 1070 G1 ROCK 8G vs ZOTAC GeForce GTX 1080 Ti ArcticStorm Mini
Overall rating
Issue date
Q2/2016Issue date
Q4/2017Overall rating
GIGABYTE GeForce GTX 1070 G1 ROCK 8G vs. ZOTAC GeForce GTX 1080 Ti ArcticStorm Mini specifications and benchmarks comparison. GIGABYTE GeForce GTX 1070 G1 ROCK 8G runs at 1.582 GHz+ 5% base clock with 8 GB GDDR5 memory, while ZOTAC GeForce GTX 1080 Ti ArcticStorm Mini runs at 1.582 GHz+ 5% base clock with 11 GB GDDR5X memory. The weight is different, — vs. —. The TDP of the first video card is 150 W and the second one is 250 W. Compare the test results to find out which video card is better.
The main differences between the models
Performance Tests
Characteristics
ReviewsMain differences between models
Reasons to choose
GIGABYTE GeForce GTX 1070 G1 ROCK 8GReport a bug
-
Higher clock frequency
1. 582 GHz+ 5% 1.506 GHz+ 2%
Approximately 5% higher clock speed
Reasons to choose
ZOTAC GeForce GTX 1080 Ti ArcticStorm MiniReport a bug
-
More memory
11GB 8GB
27% more memory
Performance tests
Exact Performance Tests GIGABYTE GeForce GTX 1070 G1 ROCK 8G vs ZOTAC GeForce GTX 1080 Ti ArcticStorm Mini
FP32 Performance (Single-precision TFLOPS)
GIGABYTE GeForce GTX 1070 G1 R. ..
6.9
ZOTAC GeForce GTX 1080 Ti Arct…
11.61
3DMark Benchmark
GIGABYTE GeForce GTX 1070 G1 R…
7061
ZOTAC GeForce GTX 1080 Ti Arct…
9982
Battlefield 5
GIGABYTE GeForce GTX 1070 G1 R…
44 fps (avg)
ZOTAC GeForce GTX 1080 Ti Arct…
65 fps (avg)
Shadow of the Tomb Raider
GIGABYTE GeForce GTX 1070 G1 R. ..
26 fps (avg)
ZOTAC GeForce GTX 1080 Ti Arct…
40 fps (avg)
Crypto-Mining Ethereum Hashrate (MH/s)
GIGABYTE GeForce GTX 1070 G1 R…
27 MH/s
ZOTAC GeForce GTX 1080 Ti Arct…
50 MH/s
Crypto-Mining Ergo Hashrate (MH/s)
GIGABYTE GeForce GTX 1070 G1 R…
57 MH/s
ZOTAC GeForce GTX 1080 Ti Arct…
99 MH/s
Crypto-Mining Ravencoin Hashrate (MH/s)
GIGABYTE GeForce GTX 1070 G1 R. ..
14 MH/s
ZOTAC GeForce GTX 1080 Ti Arct…
25 MH/s
Crypto Mining Vertcoin Hashrate (MH/s)
GIGABYTE GeForce GTX 1070 G1 R…
0.44 MH/s
ZOTAC GeForce GTX 1080 Ti Arct…
0.8MH/s
Features
Exact specifications for model comparison
GIGABYTE GeForce GTX 1070 G1 ROCK 8G
ZOTAC GeForce GTX 1080 Ti ArcticStorm Mini
GPU
gpu GIGABYTE GeForce GTX 1070 G1 ROCK 8G item
ZOTAC GeForce GTX 1080 Ti ArcticStorm Mini
AMD A4-3320M
Intel Core i7-9850HL
AMD A6-3500
Apple A12Z Bionic
AMD A6-3600
AMD Ryzen 5 3500X
MSI GeForce RTX 2070 GAMING Z 8G
INNO3D GeForce RTX 3080 Ti iCHILL X3
MSI GeForce GTX 1660 SUPER GAMING PLUS
Palit GeForce RTX 2070
AMD A6-3600
Intel Core i5-8200Y
Palit GeForce GTX 1660 Super StormX
PNY GeForce RTX 2080 XLR8 Gaming
AMD A6-3620
AMD Phenom II X3 B77
GIGABYTE AORUS Radeon RX 6800 MASTER 16G
ASUS ROG Strix GeForce GTX 1650 (GDDR6)
AMD A6-3650
AMD Ryzen 7 2800H
MSI Radeon RX 5700 Evoke GP
Colorful iGame GeForce RTX 2080 Ti Kudan-V
AMD A10-6700
Intel Core i7-11700
AMD A6-3600
Intel Core i5-8300H
Report a bugDescription of the bug
Link to source
Review of video cards based on NVIDIA GeForce GTX 1070 Ti from ASUS, Gigabyte and MSI.
Filling the Niches
12/15/17
The GTX 1070 Ti graphics cards were recently introduced. They occupied a niche between the GTX 1070 and GTX 1080. We figure out why NVIDIA needed another model on the Pascal architecture and consider several new products based on the GTX 1070 Ti from different manufacturers
See this article:
Comparison of NVIDIA GeForce GTX 1070, 1070 Ti and 1080 Reference Specifications Gaming 8G
MSI GeForce GTX 1070 Ti GAMING 8G
ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition
0003
Histograms with test results
In the GTX 10XX series of video cards, NVIDIA’s lineup of models from mid-range to high-end was lined up fairly evenly. There are clear performance steps between the GTX 1060, 1070, 1080, and 1080 Ti.
But recently NVIDIA introduced another model — the GTX 1070 Ti. It is built on the same NVIDIA Pascal architecture as the other GTX 10XX series adapters and sits between the GTX 1070 and GTX 1080.
Curiously, a year and a half has passed since the appearance of the first video card based on the Pascal architecture (GTX 1080) until the appearance of the GTX 1070 Ti.
Nothing fundamentally new in the GTX 1070 Ti . In terms of feature set and technology support, it has the same features as other models in this series.
NVIDIA GTX 1070, GTX 1070 Ti and GTX 1080 Reference Specification Comparison
If you compare NVIDIA GeForce GTX 1070 Ti with GTX 1070 and GTX 1080, you will notice that in terms of GPU characteristics (number of shader processors, texture units), the new product is closer to GTX 1080, but the memory type and memory frequency are the same as in GTX 1070 The GTX 1070 Ti and GTX 1070 use GDDR5 memory, while the GTX 1080 features more advanced GDDR5X.
Why NVIDIA Needed Another Series GTX 10 XX?
One of the possible reasons for the appearance of the GeForce GTX 1070 Ti can be the increased competition in the high-performance video card sector, associated with the appearance of the competitor’s new adapters AMD Radeon RX Vega 56 and RX Vega 64.
insure yourself a little.
Let’s also not forget about the high demand for powerful graphics cards associated with cryptocurrency mining.
There is another factor, but it is based only on rumors and conjectures. GDDR5X video memory, which is used in the GTX 1080, is more scarce and more expensive than «regular» GDDR5. Accordingly, the GTX 1070 Ti is a good backup option.
Everyone is equal, like a match
1655 operating frequencies for most participants correspond to the standard .
This situation has not been observed for quite a long time and even got used to the fact that manufacturers traditionally overestimate frequencies to one degree or another.
This is no coincidence in this case. In models based on the GTX 1070 Ti, NVIDIA has obliged graphics card manufacturers to leave the reference frequencies.
This is probably due to the fact that using a relatively small overclock of the GTX 1070 Ti graphics card will get too close in performance to the GTX 1080 and create unnecessary internal competition.
But manufacturers still have some tools with which to influence frequencies.
First of all, the actual Boost frequency of an NVIDIA GPU very often exceeds the set frequency for Boost mode. In what modes and by how much this excess will already depend on the manufacturers of video cards. In the table, we separately indicated the recorded maximum GPU frequencies of the tested video cards.
Secondly, by installing a proprietary application, you can literally in one click switch the video card to the mode provided by the manufacturer with some overclocking.
GTX 1070 Ti and mining
The topic of cryptocurrency mining with video cards is still very relevant. The GTX 1070 Ti graphics cards are just perfect for this.
They allow you to control overclocking and power consumption in a fairly wide range and you can quite finely select the settings for a particular algorithm.For most mining algorithms, as in gaming applications, you can expect GTX 1070 Ti performance levels between GTX 1070 and GTX 1080. The exception is Ethash, which is used, for example, to mine Ethereum (ETH) coins. This is where the GTX 1070 Ti can outperform the GTX 1080, as GDDR5 rather than GDDR5X memory is better suited for the Ethash algorithm.
Separately, we paid attention to the manufacturer of the memory chips of the tested video cards. The ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition, Gigabyte GeForce GTX 1070 Ti Gaming 8G, and MSI GeForce GTX 1070 Ti GAMING 8G video cards in question had memory manufactured by Micron.
Test participants
Graphics cards ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition, Gigabyte GeForce GTX 1070 Ti Gaming 8G, MSI GeForce GTX 1080 AMING0003
Three GTX 1070 graphics cards were assembled for review: ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition, Gigabyte GeForce GTX 1070 Ti Gaming 8G, and MSI GeForce GTX 1070 Ti GAMING 8G . All models have modified boards compared to the reference one and are equipped with proprietary cooling systems.
Specifications Comparison Chart
1656
Gigabyte GeForce GTX 1070 Ti Gaming 8G
You can’t call the Gigabyte GeForce GTX 1070 Ti Gaming 8G board small at all, but when all three test participants are put together, it is clearly seen that this model turned out to be the most compact among them.
The video card received an upgraded board compared to the reference one and a proprietary cooling system with a series of heat pipes and three fans.
Fans stop when GPU temperature drops below 46°C and start when temperature rises above 59°
The board will occupy no more than three expansion slots in the system.
The video card is powered by one eight-pin connector. Socket key prudently turned outward
Eight-phase power (6+2 configuration) is used compared to six-phase (5+1) in the reference GeForce GTX 1070 Ti. The manufacturer emphasizes that the heatsink touches not only the GPU, but also the video memory chips through
thermally conductive pads.The maximum temperature of the Gigabyte GeForce GTX 1070 Ti Gaming 8G GPU under load in our conditions was 67 ° C. This is a very comfortable level.
Monitoring the Gigabyte GeForce GTX 1070 Ti Gaming 8G in MSI Afterburner
The fan speed was about 1700-1800 rpm. The video card is quiet, and while running in the case, you will hardly notice the noise of this video card against the background of other components. But among other members
test is the highest value.Apparently, the effect is that it does not have such a massive radiator and slightly higher fan speeds are required.
Despite the fact that NVIDIA obliged manufacturers to leave reference frequencies for solutions based on the GTX 1070 Ti, in the Gigabyte GeForce GTX 1070 Ti Gaming 8G, presented in the test, frequencies still turned out to be slightly increased . Instead of the standard
1607/1683 MHz for the base and boost frequencies, respectively, there are frequencies of 1620/1709MHz.And in the screenshot on the right, you can see how the GPU frequency settings of the Gigabyte GeForce GTX 1070 Ti Gaming 8G (GV-N107TGAMING OC-8GD) video card change when you select the preset overclocking mode in the proprietary application compared to the factory settings (left). Data from GPU-Z
Gigabyte GeForce GTX 1070 Ti Gaming 8G frequency vs. voltage curve provided by the manufacturer
How it happened is anyone’s guess. Perhaps Gigabyte prepared this video card before the introduction of restrictions and did not remake it.
This increase, combined with the highest GPU Boost frequency we’ve recorded of any other GTX 1070 Ti-based competitor, allowed the Gigabyte GeForce GTX 1070 Ti Gaming 8G to marginally stand out from the competition in terms of performance.
Note that it is the Gigabyte GeForce GTX 1070 Ti Gaming 8G with the GV-N107TGAMING OC-8GD index that has higher frequencies (pay attention to the presence of OC in the index). The GV-N107TGAMING-8GD version operates at reference frequencies. By the way, you will not find the GV-N107TGAMING OC-8GD modification on the official website (the situation at the time of preparation of the material). The manufacturer does not want to “shine” the GTX 1070 Ti model with increased frequencies?The only backlit areas on the Gigabyte GeForce GTX 1070 Ti Gaming 8G are the Gigabyte and Fan Stop labels on the side panel. Light effects and backlight color can be customized. At the same time, Fan Stop also serves as a sensor. The inscription lights up when the fans stop
Video card control using proprietary software
The proprietary software allows you to select pre-installed board operation profiles, including overclocking mode. Various overclocking settings (frequency, power consumption, voltage, etc.) and monitoring tools are available. Not without
backlight control options. In general, a fairly standard set that can be seen in software for modern video cards from different manufacturers.. slightly higher than competitors
The MSI GeForce GTX 1070 Ti GAMING 8G board has been significantly modified from the reference board. It uses a 10-phase (8 + 2 circuit) power system, which also provides for the presence of not one eight-pin, but a bundle of two (8-pin + 6-pin) power connectors. This solution among other video cards in the review is used only here.
As many as two connectors for additional power to reduce the reviewers based on the GTX 1070 Ti, only this model has
It seems that for the MSI GeForce GTX 1070 Ti GAMING 8G they borrowed a board from the older GTX 1080.
Video memory chips are covered with a separate plate.
MSI GeForce GTX 1070 Ti GAMING 8G video card is large in height, but the manufacturer kept the width within two slots
The SO of the video card showed simply excellent efficiency of . Under load and the temperature of the GPU remained at a low level (65 ° C) and the fan speed was very low (about 1000 rpm).
MSI GeForce GTX 1070 Ti GAMING 8G monitoring in MSI Afterburner
The video card has a significant temperature reserve for overclocking experiments, but the maximum Boost frequency when working without overclocking turned out to be the most modest among the test participants.
MSI GeForce GTX 1070 Ti GAMING 8G Specifications (GPU-Z application data)
» on one of the fans and a corporate logo on the side panel.
Various glow effects can be applied to both the claws and the logo, but color selection is limited to the logo. «Claws» glow only in red.
Glowing elements MSI GeForce GTX 1070 Ti GAMING 8G
Backlight control, profile selection, various overlay diagnostic data (FPS, GPU temperature, memory usage, etc.) and many other features can be found in the proprietary MSI Gaming App.
But in our case, this application did not start (we used the latest version from the official site). Probably, the video card is still too new and the manufacturer has not yet managed to add support for it in this application.
The published screenshots of the proprietary application were taken using another MSI GAMING series video card and are provided for review.
Proprietary MSI Gaming App
Proprietary MSI Gaming App
Separate software can synchronize graphics card lighting with other compatible components such as motherboard.
Synchronization of illumination of different components in the system
Also note that MSI’s proprietary Afterburner application, which was once called RivaTuner a long time ago, is today almost the best software for overclocking and monitoring the parameters of video cards, and not only video cards MSI, as well as
of any other.MSI GeForce GTX 1070 Ti GAMING 8G Rating:
+ powerful 10-phase board
+ very quiet cooling system
+ low load fan shutdown
— the most modest boost frequency among all participants
ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition (ROG-STRIX-GTX1070TI-A8G-GAMING)
ASUS STR4
GeForce GTX 1070 Ti Advanced edition
The video card belongs to the ROG gaming product series. And from experience we can say that this automatically means the presence of a set of interesting advanced features.
The board was the largest in the test both in length and width. It will occupy three expansion slots in the system.
Unlike other GTX 1070 Ti graphics cards, this model has not one, but two HDMI ports. This may be important when using some VR systems, when you use one of the HDMI connectors to connect a monitor or TV
Service LEDs are located next to the power connector. If the power wire is not connected, the red light is on. As soon as you connect the wire, the red light will change to white. We have been seeing a similar solution on ASUS video cards of different series for more than a year
In most cases, this has little effect, but specifically in the case of my system, only this model from those participating in the test did not fit in length.
A massive heatsink pierced by numerous heat pipes is blown by three fans. The manufacturer claims that the fan mechanism is specially protected against dust according to the IP5X standard, which should ensure durability. It is curious that such a feature in relation to video card fans has not been seen before.
Fans stop when GPU temperature drops below 45°C and start when temperature rises above 57°C The Ti Advanced edition did not disappoint. The maximum GPU temperature of 63°C was the lowest in the test, and all this with a low fan speed of about 1200 rpm.
ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition monitoring in MSI Afterburner application level and demonstrate slightly higher results compared to the SD of the Gigabyte GeForce GTX 1070 Ti Gaming 8G video card.
The board in ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition is reinforced with seven power phases (configuration 6 + 1).
And in the screenshot on the right, you can see how the GPU frequency settings of the ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition video card change when you select the preset overclocking mode in the proprietary application compared to the factory settings (left). Data from GPU-Z
ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition frequency vs. voltage curve as specified by the manufacturer
, but it is higher than MSI GeForce GTX 1070 Ti GAMING 8G.
Stock and Boost clocks match those of the GTX 1070 Ti.
When installing a proprietary application, it becomes possible to select a profile with overclocking. By the way, the main difference between ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition (ROG-STRIX-GTX1070TI-A8G-GAMING) and the «regular» ROG Strix GeForce GTX 1070 Ti (ROG-STRIX-GTX1070TI-8G-GAMING) is that when When the OC Mode profile is enabled, the Advanced edition board uses slightly higher frequencies.
The lighting system in this model is the most advanced among the other participants in the review. Elements with RGB LEDs are installed both on the front panel with fans, and on the side panel (an inscription with the Republic of Gamers logo), and even on the back panel (logo), which is extremely rare.
ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition backlight
Their work profile can be associated with the GPU temperature of the video card.
Fans of the computer case can be connected to the video card and control them using the ASUS
Corporate Open Possibly ASUS Monitoring, Acceleration, Management and Setuping of the video card rather wealthy
Video Card ASUS ROG Rog Rog Rog Rog Rog The STRIX GeForce GTX 1070 Ti Advanced edition delivers excellent cooling performance and provides interesting bonus features that enthusiasts are sure to love. True, the model also stood out by the highest cost among competitive video cards based on the GTX 1070 Ti in our test.
ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition (ROG-STRIX-GTX1070TI-A8G-GAMING) rating:
+ very quiet cooling system
+ fans off at low load
+
— large dimensions
How we tested video cards
Video cards were tested without overclocking and without using branded profiles (OC, Gaming, Silence, etc. ), which usually become available when installing proprietary software.
We compared the GTX 1070 Ti-based video cards we tested with the GTX 1080, which was the MSI GeForce GTX 1080 GAMING X+ 8G, and the GTX 1070, which was the MSI GeForce GTX 1070 GAMING X 8G.
As test applications to determine the performance of video cards, we used modern games that support DirectX 11 and DirectX 12, which have built-in benchmarks. The program also includes popular synthetic tests 3DMark 11 and 3DMark (2013).
Each game used the maximum or high graphics quality settings. In games we used 2560×1440 pixel resolution . For this class of video cards, we consider this resolution to be optimal and in demand. 3DMark 11 tested graphics cards with the Extreme preset, while 3DMark (2013) used Fire Strike, Fire Strike Extreme, Fire Strike Ultra and the new DirectX 12 Time Spy test.
Maximum GPU temperature and system power consumption (without monitor) were monitored in Metro: Last Light. It was in this game that video cards, according to observations, heated up most intensively and the maximum power consumption occurred.
The system itself was operated outside the PC case (open bench) at a room temperature of about 21 °C. The noise level created by the operation of video card cooling systems was evaluated subjectively.
The final score in the Performance category was based on all tests. At the same time, gaming tests, 3DMark 11 Extreme test, 3DMark: Time Spy test had the same weight in the final score. And the total weight of all 3DMark: Fire Strike tests was equal to the weight of one of the gaming tests.
Histograms are normalized as a percentage with models sorted by test results. Specific results in terms of scores and FPS are also listed.
Configuration of the test platform:
Processor: Intel Core i7-3770K, Angelled to 4.2 MHz
Maternal board: Biostar Hi-Fi Z77X
DDR3 1600
Storage: SSD Adata S511 120 GB (system), HDD 1 TB
Operating system: Windows 10 Pro 64 bit
NVIDIA driver used for all video cards: GeForce 388. 31
Test results ensuring silent operation in the absence of load. Here are the measurements of GPU temperatures at which the fans are turned off and activated for the tested video cards
GTA V 2560×1440, FPS
Metro: Last Light 2560×1440, FPS
Far Cry Primal 2560×1440, FPS
HITMAN 2016 2560 × 1440, FPS
Tom Clancy’s Ghost Recon Wildlands
Total War: Warhammer II 2560 × 1460 × 1460 × 1460 ×0003
Rise of the Tomb Raider 2560×1440, FPS
3DMark 11 Extreme,
3DMark: Fire Strike, GPU-
3DMARK: Fire Strike Extreme, GPU-Balls
3DMARK: Fire Strike Ultra, GPU-Balls
3DMARK: TIL1656
Productivity
Productivity/energy consumption
The temperature of the graphic processor under load, ° C (less — better) 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 systems in the game, W (less is better)
0003
Note that the GTX 1070 and GTX 1080 were not reference models, but MSI video cards with some factory overclocking. Please also note that the MSI GeForce GTX 1080 GAMING X+ 8G model included in the comparison is a modified GTX 1080 with increased memory frequency.
Speed ASUS ROG STRIX GeForce GTX 1070 Ti Advanced 1655 edition, Gigabyte GeForce GTX 1070 Ti Gaming 8 G and MSI
5 GeForce GTX 1070 were very close This is logical, given that they operate at almost identical frequencies. From the histograms, you can see that the Gigabyte card is a little ahead, but you most likely won’t be able to notice this difference without special measurements.
This state of affairs makes it very difficult to identify the best models.
Absolutely all the GTX 1070 Ti cards in this test are excellent devices without noticeable flaws. There are some differences in dimensions: the three-fan Gigabyte GeForce GTX 1070 Ti Gaming 8G turned out to be the most compact, and the three-fan ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition was the largest.
ASUS, Gigabyte, MSI cooling systems cope with heat dissipation without any problems and keep the GPU temperature within safe limits, leaving some room for overclocking experiments. By the way, with overclocking, these video cards based on the GTX 1070 Ti may well approach or equal the speed of the GTX 1080.
The ASUS ROG STRIX GeForce GTX 1070 Ti Advanced edition turned out to be the most interesting in terms of external lighting design. It has the most advanced lighting system, but it also costs a little more than other participants.
Like other Pascal architecture graphics cards, the GTX 1070 Ti-based models have an excellent performance/power ratio. According to this indicator, NVIDIA solutions have significantly outperformed competitors based on AMD GPUs in recent years.
An interesting situation: according to NVIDIA, the power consumption of the GTX 1070 Ti should be higher than the GTX 1070 and be at the level of the GTX 1080. But according to our measurements, the GTX 1070 Ti and GTX 1070 video cards are almost on the same level in this indicator, but the power consumption of the GTX 1080 turned out to be higher.
The cost of GTX 1070 Ti video cards in our market is almost one and a half times higher than NVIDIA’s recommended prices. This is partly due to the novelty — models only appear on sale. But this is also influenced by pricing features (we have video cards traditionally more expensive than, for example, the US market), as well as additional demand due to the popularization of mining by video cards.
With the release of the GTX 1070 Ti, the graphics card market didn’t change much. It’s just that NVIDIA has filled a small niche between their own video cards.
At the same time, the user has an additional opportunity to more finely select a video card according to his budget in the class of high-end video cards.
- 5. 83 TFLOPS over FLOPS?