GeForce GT 640M vs GTX 660M
Aggregate performance score
We've compared GeForce GTX 660M and GeForce GT 640M, covering specs and all relevant benchmarks.
GTX 660M outperforms GT 640M by an impressive 57% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 707 | 843 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 5.15 | 5.14 |
| Architecture | Kepler (2012−2018) | Kepler (2012−2018) |
| GPU code name | GK107 | GK107 |
| Market segment | Laptop | Laptop |
| Release date | 22 March 2012 (12 years ago) | 22 March 2012 (12 years ago) |
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 | 384 | 384 |
| Core clock speed | 835 MHz | Up to 625 MHz |
| Boost clock speed | 950 MHz | 645 MHz |
| Number of transistors | 1,270 million | 1,270 million |
| Manufacturing process technology | 28 nm | 28 nm |
| Power consumption (TDP) | 50 Watt | 32 Watt |
| Texture fill rate | 30.40 | 20.00 |
| Floating-point processing power | 0.7296 TFLOPS | 0.48 TFLOPS |
| ROPs | 16 | 16 |
| TMUs | 32 | 32 |
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).
| Laptop size | large | medium sized |
| Bus support | PCI Express 2.0, PCI Express 3.0 | PCI Express 2.0, PCI Express 3.0 |
| Interface | MXM-B (3.0) | PCIe 3.0 x16 |
| 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 | DDR3\GDDR5 |
| Maximum RAM amount | 1 GB | 2 GB |
| Memory bus width | 128bit | 128bit |
| Memory clock speed | 2000 MHz | 900 MHz |
| Memory bandwidth | 64.0 GB/s | Up to 64.0 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 | No outputs | No outputs |
| HDMI | + | + |
| HDCP | + | + |
| Maximum VGA resolution | Up to 2048x1536 | Up to 2048x1536 |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| 3D Blu-Ray | - | + |
| Optimus | + | + |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 API | 12 API |
| Shader Model | 5.1 | 5.1 |
| OpenGL | 4.5 | 4.5 |
| OpenCL | 1.1 | 1.1 |
| Vulkan | 1.1.126 | 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 11 Performance GPU
3DMark 11 is an obsolete DirectX 11 benchmark by Futuremark. It used four tests based on two scenes, one being few submarines exploring the submerged wreck of a sunken ship, the other is an abandoned temple deep in the jungle. All the tests are heavy with volumetric lighting and tessellation, and despite being done in 1280x720 resolution, are relatively taxing. Discontinued in January 2020, 3DMark 11 is now superseded by Time Spy.
3DMark Vantage Performance
3DMark Vantage is an outdated DirectX 10 benchmark using 1280x1024 screen resolution. It taxes the graphics card with two scenes, one depicting a girl escaping some militarized base located within a sea cave, the other displaying a space fleet attack on a defenseless planet. It was discontinued in April 2017, and Time Spy benchmark is now recommended to be used instead.
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.
3DMark Cloud Gate GPU
Cloud Gate is an outdated DirectX 11 feature level 10 benchmark that was used for home PCs and basic notebooks. It displays a few scenes of some weird space teleportation device launching spaceships into unknown, using fixed resolution of 1280x720. Just like Ice Storm benchmark, it has been discontinued in January 2020 and replaced by 3DMark Night Raid.
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.
Octane Render OctaneBench
This is a special benchmark measuring graphics card performance in OctaneRender, which is a realistic GPU rendering engine by OTOY Inc., available either as a standalone program, or as a plugin for 3DS Max, Cinema 4D and many other apps. It renders four different static scenes, then compares render times with a reference GPU which is currently GeForce GTX 980. This benchmark has nothing to do with gaming and is aimed at professional 3D graphics artists.
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:
| 900p | 32
+23.1%
| 26
−23.1%
|
| Full HD | 35
+59.1%
| 22
−59.1%
|
| 1200p | 38
+100%
| 19
−100%
|
FPS performance in popular games
Full HD
Low Preset
| Cyberpunk 2077 | 7−8
+40%
|
5−6
−40%
|
Full HD
Medium Preset
| Assassin's Creed Odyssey | 10−12
+37.5%
|
8−9
−37.5%
|
| Assassin's Creed Valhalla | 3−4
+200%
|
1−2
−200%
|
| Battlefield 5 | 8−9
+167%
|
3−4
−167%
|
| Call of Duty: Modern Warfare | 8−9
+33.3%
|
6−7
−33.3%
|
| Cyberpunk 2077 | 7−8
+40%
|
5−6
−40%
|
| Far Cry 5 | 8−9
+100%
|
4−5
−100%
|
| Far Cry New Dawn | 10−11
+66.7%
|
6−7
−66.7%
|
| Forza Horizon 4 | 21−24
+100%
|
10−12
−100%
|
| Hitman 3 | 9−10
+28.6%
|
7−8
−28.6%
|
| Horizon Zero Dawn | 24−27
+30%
|
20−22
−30%
|
| Metro Exodus | 7−8
+600%
|
1−2
−600%
|
| Red Dead Redemption 2 | 9−10
+80%
|
5−6
−80%
|
| Shadow of the Tomb Raider | 14−16
+27.3%
|
10−12
−27.3%
|
| Watch Dogs: Legion | 40−45
+13.5%
|
35−40
−13.5%
|
Full HD
High Preset
| Assassin's Creed Odyssey | 10−12
+37.5%
|
8−9
−37.5%
|
| Assassin's Creed Valhalla | 3−4
+200%
|
1−2
−200%
|
| Battlefield 5 | 8−9
+167%
|
3−4
−167%
|
| Call of Duty: Modern Warfare | 8−9
+33.3%
|
6−7
−33.3%
|
| Cyberpunk 2077 | 7−8
+40%
|
5−6
−40%
|
| Far Cry 5 | 8−9
+100%
|
4−5
−100%
|
| Far Cry New Dawn | 10−11
+66.7%
|
6−7
−66.7%
|
| Forza Horizon 4 | 21−24
+100%
|
10−12
−100%
|
| Hitman 3 | 9−10
+28.6%
|
7−8
−28.6%
|
| Horizon Zero Dawn | 24−27
+30%
|
20−22
−30%
|
| Metro Exodus | 7−8
+600%
|
1−2
−600%
|
| Red Dead Redemption 2 | 9−10
+80%
|
5−6
−80%
|
| Shadow of the Tomb Raider | 14−16
+27.3%
|
10−12
−27.3%
|
| The Witcher 3: Wild Hunt | 14−16
−20%
|
18
+20%
|
| Watch Dogs: Legion | 40−45
+13.5%
|
35−40
−13.5%
|
Full HD
Ultra Preset
| Assassin's Creed Odyssey | 10−12
+37.5%
|
8−9
−37.5%
|
| Assassin's Creed Valhalla | 3−4
+200%
|
1−2
−200%
|
| Call of Duty: Modern Warfare | 8−9
+33.3%
|
6−7
−33.3%
|
| Cyberpunk 2077 | 7−8
+40%
|
5−6
−40%
|
| Far Cry 5 | 8−9
+100%
|
4−5
−100%
|
| Forza Horizon 4 | 21−24
+100%
|
10−12
−100%
|
| Hitman 3 | 9−10
+28.6%
|
7−8
−28.6%
|
| Horizon Zero Dawn | 24−27
+30%
|
20−22
−30%
|
| Shadow of the Tomb Raider | 14−16
+27.3%
|
10−12
−27.3%
|
| The Witcher 3: Wild Hunt | 14−16
+15.4%
|
12−14
−15.4%
|
| Watch Dogs: Legion | 40−45
+13.5%
|
35−40
−13.5%
|
Full HD
Epic Preset
| Red Dead Redemption 2 | 9−10
+80%
|
5−6
−80%
|
1440p
High Preset
| Battlefield 5 | 7−8
+75%
|
4−5
−75%
|
| Far Cry New Dawn | 6−7
+50%
|
4−5
−50%
|
1440p
Ultra Preset
| Assassin's Creed Odyssey | 3−4
+50%
|
2−3
−50%
|
| Call of Duty: Modern Warfare | 3−4
+200%
|
1−2
−200%
|
| Cyberpunk 2077 | 2−3
+100%
|
1−2
−100%
|
| Far Cry 5 | 4−5
+33.3%
|
3−4
−33.3%
|
| Forza Horizon 4 | 3−4
+200%
|
1−2
−200%
|
| Hitman 3 | 8−9
+14.3%
|
7−8
−14.3%
|
| Horizon Zero Dawn | 9−10
+50%
|
6−7
−50%
|
| The Witcher 3: Wild Hunt | 3−4
+50%
|
2−3
−50%
|
| Watch Dogs: Legion | 21−24
+64.3%
|
14−16
−64.3%
|
1440p
Epic Preset
| Red Dead Redemption 2 | 7−8
+40%
|
5−6
−40%
|
4K
High Preset
| Battlefield 5 | 2−3 | 0−1 |
| Far Cry New Dawn | 2−3
+100%
|
1−2
−100%
|
| Metro Exodus | 0−1 | 0−1 |
4K
Ultra Preset
| Assassin's Creed Odyssey | 3−4
+50%
|
2−3
−50%
|
| Assassin's Creed Valhalla | 2−3
+100%
|
1−2
−100%
|
| Call of Duty: Modern Warfare | 1−2
+0%
|
1−2
+0%
|
| Cyberpunk 2077 | 0−1 | 0−1 |
| Far Cry 5 | 2−3
+100%
|
1−2
−100%
|
| Forza Horizon 4 | 2−3
+100%
|
1−2
−100%
|
| Watch Dogs: Legion | 1−2 | 0−1 |
4K
Epic Preset
| Red Dead Redemption 2 | 5−6
+66.7%
|
3−4
−66.7%
|
This is how GTX 660M and GT 640M compete in popular games:
- GTX 660M is 23% faster in 900p
- GTX 660M is 59% faster in 1080p
- GTX 660M is 100% faster in 1200p
Here's the range of performance differences observed across popular games:
- in Metro Exodus, with 1080p resolution and the Medium Preset, the GTX 660M is 600% faster.
- in The Witcher 3: Wild Hunt, with 1080p resolution and the High Preset, the GT 640M is 20% faster.
All in all, in popular games:
- GTX 660M is ahead in 54 tests (96%)
- GT 640M is ahead in 1 test (2%)
- there's a draw in 1 test (2%)
Pros & cons summary
| Performance score | 3.76 | 2.40 |
| Maximum RAM amount | 1 GB | 2 GB |
| Power consumption (TDP) | 50 Watt | 32 Watt |
GTX 660M has a 56.7% higher aggregate performance score.
GT 640M, on the other hand, has a 100% higher maximum VRAM amount, and 56.3% lower power consumption.
The GeForce GTX 660M is our recommended choice as it beats the GeForce GT 640M in performance tests.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Comparisons with similar GPUs
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
