GeForce GT 640M LE vs GTX 970
Aggregate performance score
We've compared GeForce GTX 970 with GeForce GT 640M LE, including specs and performance data.
GTX 970 outperforms 640M LE by a whopping 1280% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 268 | 983 |
| Place by popularity | 77 | not in top-100 |
| Cost-effectiveness evaluation | 12.09 | 0.02 |
| Power efficiency | 11.95 | 4.01 |
| Architecture | Maxwell 2.0 (2014−2019) | Fermi (2010−2014) |
| GPU code name | GM204 | GF108 |
| Market segment | Desktop | Laptop |
| Release date | 19 September 2014 (11 years ago) | 4 May 2012 (13 years ago) |
| Launch price (MSRP) | $329 | $849.99 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
GTX 970 has 60350% better value for money than GT 640M LE.
Performance to price scatter graph
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 | 1664 | Up to 384 |
| Core clock speed | 1050 MHz | Up to 500 MHz |
| Boost clock speed | 1178 MHz | no data |
| Number of transistors | 5,200 million | 585 million |
| Manufacturing process technology | 28 nm | 40 nm |
| Power consumption (TDP) | 148 Watt | 20 Watt |
| Maximum GPU temperature | 98 °C | no data |
| Texture fill rate | 122.5 | 12.05 |
| Floating-point processing power | 3.92 TFLOPS | 0.289 TFLOPS |
| ROPs | 56 | 4 |
| TMUs | 104 | 16 |
| L1 Cache | 624 KB | 128 KB |
| L2 Cache | 2 MB | 256 KB |
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 | no data | medium sized |
| Bus support | PCI Express 3.0 | PCI Express 2.0, PCI Express 3.0 |
| Interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
| Length | 267 mm | no data |
| Height | 4.376" (11.1 cm) | no data |
| Width | 2-slot | no data |
| Recommended system power (PSU) | 500 Watt | no data |
| Supplementary power connectors | 2x 6-pin | no data |
| 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\DDR5 |
| Maximum RAM amount | 4 GB | 2 GB |
| Memory bus width | 256 Bit | 128bit |
| Memory clock speed | 7.0 GB/s | 785 MHz |
| Memory bandwidth | 224 GB/s | Up to 28.8 GB/s |
| Shared memory | - | - |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | Dual Link DVI-I, HDMI 2.0, 3x DisplayPort 1.2 | No outputs |
| Multi monitor support | 4 displays | no data |
| HDMI | + | + |
| HDCP | + | + |
| Maximum VGA resolution | 2048x1536 | Up to 2048x1536 |
| G-SYNC support | + | - |
| Audio input for HDMI | Internal | no data |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| 3D Blu-Ray | - | + |
| GameStream | + | - |
| GeForce ShadowPlay | + | - |
| GPU Boost | 2.0 | no data |
| GameWorks | + | - |
| Optimus | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_1) | 12 API |
| Shader Model | 6.4 | 5.1 |
| OpenGL | 4.4 | 4.5 |
| OpenCL | 1.2 | 1.1 |
| Vulkan | 1.1.126 | N/A |
| CUDA | + | + |
Synthetic benchmarks
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.
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.
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.
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 | 260−270
+1268%
| 19
−1268%
|
| Full HD | 81
+286%
| 21
−286%
|
| 1440p | 54
+1700%
| 3−4
−1700%
|
| 4K | 39
+1850%
| 2−3
−1850%
|
Cost per frame, $
| 1080p | 4.06
+897%
| 40.48
−897%
|
| 1440p | 6.09
+4550%
| 283.33
−4550%
|
| 4K | 8.44
+4938%
| 425.00
−4938%
|
- GTX 970 has 897% lower cost per frame in 1080p
- GTX 970 has 4550% lower cost per frame in 1440p
- GTX 970 has 4938% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 130−140
+6550%
|
2−3
−6550%
|
| Cyberpunk 2077 | 50−55
+1175%
|
4−5
−1175%
|
Full HD
Medium
| Battlefield 5 | 90−95
+3033%
|
3−4
−3033%
|
| Counter-Strike 2 | 130−140
+6550%
|
2−3
−6550%
|
| Cyberpunk 2077 | 50−55
+1175%
|
4−5
−1175%
|
| Escape from Tarkov | 90−95
+1720%
|
5−6
−1720%
|
| Far Cry 5 | 75−80
+1800%
|
4−5
−1800%
|
| Fortnite | 110−120
+1850%
|
6−7
−1850%
|
| Forza Horizon 4 | 90−95
+933%
|
9−10
−933%
|
| Forza Horizon 5 | 70−75
+2367%
|
3−4
−2367%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 90−95
+820%
|
10−11
−820%
|
| Valorant | 160−170
+343%
|
35−40
−343%
|
Full HD
High
| Battlefield 5 | 90−95
+3033%
|
3−4
−3033%
|
| Counter-Strike 2 | 130−140
+6550%
|
2−3
−6550%
|
| Counter-Strike: Global Offensive | 250−260
+608%
|
35−40
−608%
|
| Cyberpunk 2077 | 50−55
+1175%
|
4−5
−1175%
|
| Dota 2 | 120−130
+505%
|
20−22
−505%
|
| Escape from Tarkov | 90−95
+1720%
|
5−6
−1720%
|
| Far Cry 5 | 75−80
+1800%
|
4−5
−1800%
|
| Fortnite | 82
+1267%
|
6−7
−1267%
|
| Forza Horizon 4 | 90−95
+933%
|
9−10
−933%
|
| Forza Horizon 5 | 70−75
+2367%
|
3−4
−2367%
|
| Grand Theft Auto V | 71
+3450%
|
2−3
−3450%
|
| Metro Exodus | 39
+1200%
|
3−4
−1200%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 90−95
+820%
|
10−11
−820%
|
| The Witcher 3: Wild Hunt | 81
+913%
|
8−9
−913%
|
| Valorant | 160−170
+343%
|
35−40
−343%
|
Full HD
Ultra
| Battlefield 5 | 48
+1500%
|
3−4
−1500%
|
| Cyberpunk 2077 | 50−55
+1175%
|
4−5
−1175%
|
| Dota 2 | 120−130
+505%
|
20−22
−505%
|
| Escape from Tarkov | 90−95
+1720%
|
5−6
−1720%
|
| Far Cry 5 | 75−80
+1800%
|
4−5
−1800%
|
| Forza Horizon 4 | 90−95
+933%
|
9−10
−933%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 52
+420%
|
10−11
−420%
|
| The Witcher 3: Wild Hunt | 43
+438%
|
8−9
−438%
|
| Valorant | 160−170
+343%
|
35−40
−343%
|
Full HD
Epic
| Fortnite | 60
+900%
|
6−7
−900%
|
1440p
High
| Counter-Strike 2 | 50−55
+900%
|
5−6
−900%
|
| Counter-Strike: Global Offensive | 160−170
+1292%
|
12−14
−1292%
|
| Grand Theft Auto V | 40−45
+1333%
|
3−4
−1333%
|
| Metro Exodus | 24
+2300%
|
1−2
−2300%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+929%
|
16−18
−929%
|
| Valorant | 200−210
+1910%
|
10−11
−1910%
|
1440p
Ultra
| Battlefield 5 | 65−70
+1550%
|
4−5
−1550%
|
| Cyberpunk 2077 | 21−24
+2200%
|
1−2
−2200%
|
| Escape from Tarkov | 50−55
+1225%
|
4−5
−1225%
|
| Far Cry 5 | 50−55
+2600%
|
2−3
−2600%
|
| Forza Horizon 4 | 60−65
+1400%
|
4−5
−1400%
|
| The Witcher 3: Wild Hunt | 35−40
+1133%
|
3−4
−1133%
|
1440p
Epic
| Fortnite | 55−60
+1767%
|
3−4
−1767%
|
4K
High
| Counter-Strike 2 | 21−24
+2200%
|
1−2
−2200%
|
| Grand Theft Auto V | 46
+229%
|
14−16
−229%
|
| Metro Exodus | 13 | 0−1 |
| The Witcher 3: Wild Hunt | 29
+1350%
|
2−3
−1350%
|
| Valorant | 130−140
+1613%
|
8−9
−1613%
|
4K
Ultra
| Battlefield 5 | 20
+1900%
|
1−2
−1900%
|
| Counter-Strike 2 | 21−24
+2200%
|
1−2
−2200%
|
| Cyberpunk 2077 | 10−11 | 0−1 |
| Dota 2 | 75−80
+2500%
|
3−4
−2500%
|
| Escape from Tarkov | 24−27 | 0−1 |
| Far Cry 5 | 27−30 | 0−1 |
| Forza Horizon 4 | 40−45
+1950%
|
2−3
−1950%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18
+500%
|
3−4
−500%
|
4K
Epic
| Fortnite | 22
+633%
|
3−4
−633%
|
This is how GTX 970 and GT 640M LE compete in popular games:
- GTX 970 is 1268% faster in 900p
- GTX 970 is 286% faster in 1080p
- GTX 970 is 1700% faster in 1440p
- GTX 970 is 1850% faster in 4K
Here's the range of performance differences observed across popular games:
- in Counter-Strike 2, with 1080p resolution and the Low Preset, the GTX 970 is 6550% faster.
All in all, in popular games:
- Without exception, GTX 970 surpassed GT 640M LE in all 52 of our tests.
Pros & cons summary
| Performance score | 23.04 | 1.67 |
| Recency | 19 September 2014 | 4 May 2012 |
| Maximum RAM amount | 4 GB | 2 GB |
| Chip lithography | 28 nm | 40 nm |
| Power consumption (TDP) | 148 Watt | 20 Watt |
GTX 970 has a 1279.6% higher aggregate performance score, an age advantage of 2 years, a 100% higher maximum VRAM amount, and a 42.9% more advanced lithography process.
GT 640M LE, on the other hand, has 640% lower power consumption.
The GeForce GTX 970 is our recommended choice as it beats the GeForce GT 640M LE in performance tests.
Be aware that GeForce GTX 970 is a desktop graphics card while GeForce GT 640M LE is a notebook one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
