GeForce GTX 660 vs GTX 1070
Aggregate performance score
We've compared GeForce GTX 1070 and GeForce GTX 660, covering specs and all relevant benchmarks.
GTX 1070 outperforms GTX 660 by a whopping 237% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 146 | 439 |
| Place by popularity | 32 | 81 |
| Cost-effectiveness evaluation | 23.29 | 3.40 |
| Power efficiency | 16.12 | 5.13 |
| Architecture | Pascal (2016−2021) | Kepler (2012−2018) |
| GPU code name | GP104 | GK106 |
| Market segment | Desktop | Desktop |
| Release date | 10 June 2016 (8 years ago) | 6 September 2012 (12 years ago) |
| Launch price (MSRP) | $379 | $229 |
Cost-effectiveness evaluation
Performance to price ratio. The higher, the better.
GTX 1070 has 585% better value for money than GTX 660.
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 1920 | 960 |
| Core clock speed | 1506 MHz | 980 MHz |
| Boost clock speed | 1683 MHz | 1033 MHz |
| Number of transistors | 7,200 million | 2,540 million |
| Manufacturing process technology | 16 nm | 28 nm |
| Power consumption (TDP) | 150 Watt | 140 Watt |
| Maximum GPU temperature | 94 °C | no data |
| Texture fill rate | 202.0 | 82.56 |
| Floating-point processing power | 6.463 TFLOPS | 1.981 TFLOPS |
| ROPs | 64 | 24 |
| TMUs | 120 | 80 |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Bus support | PCIe 3.0 | PCI Express 3.0 |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Length | 267 mm | 241 mm |
| Height | 4.376" (11.1 cm) | 4.376" (11.1 cm) |
| Width | 2-slot | 2-slot |
| Recommended system power (PSU) | 500 Watt | no data |
| Supplementary power connectors | 1x 8-pin | 1x 6-pin |
| SLI options | + | + |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR5 | GDDR5 |
| Maximum RAM amount | 8 GB | 2 GB |
| Memory bus width | 256 Bit | 192-bit GDDR5 |
| Memory clock speed | 8 GB/s | 6.0 GB/s |
| Memory bandwidth | 256 GB/s | 144.2 GB/s |
| Shared memory | - | - |
Connectivity and outputs
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
| Display Connectors | DP 1.42, HDMI 2.0b, Dual Link-DVI | One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort |
| Multi monitor support | + | 4 displays |
| HDMI | + | + |
| HDCP | - | + |
| Maximum VGA resolution | no data | 2048x1536 |
| G-SYNC support | + | - |
| Audio input for HDMI | no data | Internal |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| 3D Blu-Ray | - | + |
| 3D Gaming | - | + |
| 3D Vision | - | + |
| GPU Boost | 3.0 | no data |
| VR Ready | + | no data |
| Ansel | + | no data |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_1) | 12 (11_0) |
| Shader Model | 6.4 | 5.1 |
| OpenGL | 4.5 | 4.3 |
| OpenCL | 1.2 | 1.2 |
| Vulkan | + | 1.1.126 |
| CUDA | + | + |
Synthetic benchmark performance
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score. We are regularly improving our combining algorithms, but if you find some perceived inconsistencies, feel free to speak up in comments section, we usually fix problems quickly.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
3DMark Fire Strike Graphics
Fire Strike is a DirectX 11 benchmark for gaming PCs. It features two separate tests displaying a fight between a humanoid and a fiery creature made of lava. Using 1920x1080 resolution, Fire Strike shows off some realistic graphics and is quite taxing on hardware.
GeekBench 5 OpenCL
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.
GeekBench 5 Vulkan
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses Vulkan API by AMD & Khronos Group.
GeekBench 5 CUDA
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses CUDA API by NVIDIA.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| Full HD | 115
+145%
| 47
−145%
|
| 1440p | 67
+272%
| 18−20
−272%
|
| 4K | 50
+257%
| 14−16
−257%
|
Cost per frame, $
| 1080p | 3.30
+47.8%
| 4.87
−47.8%
|
| 1440p | 5.66
+125%
| 12.72
−125%
|
| 4K | 7.58
+116%
| 16.36
−116%
|
- GTX 1070 has 48% lower cost per frame in 1080p
- GTX 1070 has 125% lower cost per frame in 1440p
- GTX 1070 has 116% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 70−75
+238%
|
21−24
−238%
|
| Cyberpunk 2077 | 70−75
+252%
|
21−24
−252%
|
| Elden Ring | 120−130
+246%
|
35−40
−246%
|
Full HD
Medium Preset
| Battlefield 5 | 87
+263%
|
24−27
−263%
|
| Counter-Strike 2 | 70−75
+238%
|
21−24
−238%
|
| Cyberpunk 2077 | 70−75
+252%
|
21−24
−252%
|
| Forza Horizon 4 | 160−170
+269%
|
45−50
−269%
|
| Metro Exodus | 107
+257%
|
30−33
−257%
|
| Red Dead Redemption 2 | 115
+283%
|
30−33
−283%
|
| Valorant | 140−150
+250%
|
40−45
−250%
|
Full HD
High Preset
| Battlefield 5 | 156
+247%
|
45−50
−247%
|
| Counter-Strike 2 | 70−75
+238%
|
21−24
−238%
|
| Cyberpunk 2077 | 70−75
+252%
|
21−24
−252%
|
| Dota 2 | 74
+252%
|
21−24
−252%
|
| Elden Ring | 120−130
+246%
|
35−40
−246%
|
| Far Cry 5 | 75
+257%
|
21−24
−257%
|
| Fortnite | 150
+275%
|
40−45
−275%
|
| Forza Horizon 4 | 160−170
+269%
|
45−50
−269%
|
| Grand Theft Auto V | 111
+270%
|
30−33
−270%
|
| Metro Exodus | 75
+257%
|
21−24
−257%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 225
+246%
|
65−70
−246%
|
| Red Dead Redemption 2 | 43
+258%
|
12−14
−258%
|
| The Witcher 3: Wild Hunt | 52
+271%
|
14−16
−271%
|
| Valorant | 140−150
+250%
|
40−45
−250%
|
| World of Tanks | 270−280
+249%
|
80−85
−249%
|
Full HD
Ultra Preset
| Battlefield 5 | 74
+252%
|
21−24
−252%
|
| Counter-Strike 2 | 70−75
+238%
|
21−24
−238%
|
| Cyberpunk 2077 | 70−75
+252%
|
21−24
−252%
|
| Dota 2 | 110−120
+277%
|
30−33
−277%
|
| Far Cry 5 | 90−95
+241%
|
27−30
−241%
|
| Forza Horizon 4 | 160−170
+269%
|
45−50
−269%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 94
+248%
|
27−30
−248%
|
| Valorant | 140−150
+250%
|
40−45
−250%
|
1440p
High Preset
| Dota 2 | 60−65
+256%
|
18−20
−256%
|
| Elden Ring | 65−70
+283%
|
18−20
−283%
|
| Grand Theft Auto V | 60−65
+256%
|
18−20
−256%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+250%
|
50−55
−250%
|
| Red Dead Redemption 2 | 27
+238%
|
8−9
−238%
|
| World of Tanks | 220−230
+245%
|
65−70
−245%
|
1440p
Ultra Preset
| Battlefield 5 | 67
+272%
|
18−20
−272%
|
| Counter-Strike 2 | 30−35
+267%
|
9−10
−267%
|
| Cyberpunk 2077 | 30−35
+240%
|
10−11
−240%
|
| Far Cry 5 | 110−120
+273%
|
30−33
−273%
|
| Forza Horizon 4 | 95−100
+267%
|
27−30
−267%
|
| Metro Exodus | 71
+238%
|
21−24
−238%
|
| The Witcher 3: Wild Hunt | 55−60
+263%
|
16−18
−263%
|
| Valorant | 100−110
+250%
|
30−33
−250%
|
4K
High Preset
| Counter-Strike 2 | 35−40
+250%
|
10−11
−250%
|
| Dota 2 | 62
+244%
|
18−20
−244%
|
| Elden Ring | 30−35
+256%
|
9−10
−256%
|
| Grand Theft Auto V | 62
+244%
|
18−20
−244%
|
| Metro Exodus | 23
+283%
|
6−7
−283%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95
+252%
|
27−30
−252%
|
| Red Dead Redemption 2 | 18
+260%
|
5−6
−260%
|
| The Witcher 3: Wild Hunt | 62
+244%
|
18−20
−244%
|
4K
Ultra Preset
| Battlefield 5 | 37
+270%
|
10−11
−270%
|
| Counter-Strike 2 | 35−40
+250%
|
10−11
−250%
|
| Cyberpunk 2077 | 14−16
+250%
|
4−5
−250%
|
| Dota 2 | 65−70
+272%
|
18−20
−272%
|
| Far Cry 5 | 50−55
+257%
|
14−16
−257%
|
| Fortnite | 44
+267%
|
12−14
−267%
|
| Forza Horizon 4 | 55−60
+256%
|
16−18
−256%
|
| Valorant | 50−55
+238%
|
16−18
−238%
|
This is how GTX 1070 and GTX 660 compete in popular games:
- GTX 1070 is 145% faster in 1080p
- GTX 1070 is 272% faster in 1440p
- GTX 1070 is 257% faster in 4K
Pros & cons summary
| Performance score | 35.13 | 10.43 |
| Recency | 10 June 2016 | 6 September 2012 |
| Maximum RAM amount | 8 GB | 2 GB |
| Chip lithography | 16 nm | 28 nm |
| Power consumption (TDP) | 150 Watt | 140 Watt |
GTX 1070 has a 236.8% higher aggregate performance score, an age advantage of 3 years, a 300% higher maximum VRAM amount, and a 75% more advanced lithography process.
GTX 660, on the other hand, has 7.1% lower power consumption.
The GeForce GTX 1070 is our recommended choice as it beats the GeForce GTX 660 in performance tests.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
