L40 vs GeForce GTX 670MX
Aggregate performance score
We've compared GeForce GTX 670MX with L40, including specs and performance data.
L40 outperforms 670MX by a whopping 1036% 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 | 691 | 62 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 4.86 | 13.79 |
| Architecture | Kepler (2012−2018) | Ada Lovelace (2022−2024) |
| GPU code name | GK104 | AD102 |
| Market segment | Laptop | Workstation |
| Release date | 1 October 2012 (13 years ago) | 13 October 2022 (3 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 | 960 | 18176 |
| Core clock speed | 600 MHz | 735 MHz |
| Boost clock speed | no data | 2490 MHz |
| Number of transistors | 3,540 million | 76,300 million |
| Manufacturing process technology | 28 nm | 4 nm |
| Power consumption (TDP) | 75 Watt | 300 Watt |
| Texture fill rate | 48.08 | 1,414 |
| Floating-point processing power | 1.154 TFLOPS | 90.52 TFLOPS |
| ROPs | 24 | 192 |
| TMUs | 80 | 568 |
| Tensor Cores | no data | 568 |
| Ray Tracing Cores | no data | 142 |
| L1 Cache | 80 KB | 17.8 MB |
| L2 Cache | 384 KB | 96 MB |
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 | no data |
| Bus support | PCI Express 2.0 | no data |
| Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Length | no data | 267 mm |
| Width | no data | 2-slot |
| Supplementary power connectors | no data | 1x 16-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 | GDDR6 |
| Maximum RAM amount | 3 GB | 48 GB |
| Memory bus width | 192 Bit | 384 Bit |
| Memory clock speed | 1400 MHz | 2250 MHz |
| Memory bandwidth | 67.2 GB/s | 864.0 GB/s |
| Shared memory | - | - |
| Resizable BAR | - | + |
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 | No outputs | 4x DisplayPort 1.4a |
| HDMI | + | - |
| HDCP | + | - |
| Maximum VGA resolution | Up to 2048x1536 | no data |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| Optimus | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 API | 12 Ultimate (12_2) |
| Shader Model | 5.1 | 6.7 |
| OpenGL | 4.5 | 4.6 |
| OpenCL | 1.1 | 3.0 |
| Vulkan | 1.1.126 | 1.3 |
| CUDA | + | 8.9 |
| DLSS | - | + |
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.
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.
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 | 40
−1025%
| 450−500
+1025%
|
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 21−24
−995%
|
230−240
+995%
|
| Cyberpunk 2077 | 10−11
−1000%
|
110−120
+1000%
|
| Resident Evil 4 Remake | 7−8
−971%
|
75−80
+971%
|
Full HD
Medium
| Battlefield 5 | 20−22
−1000%
|
220−230
+1000%
|
| Counter-Strike 2 | 21−24
−995%
|
230−240
+995%
|
| Cyberpunk 2077 | 10−11
−1000%
|
110−120
+1000%
|
| Far Cry 5 | 14−16
−1033%
|
170−180
+1033%
|
| Fortnite | 27−30
−971%
|
300−310
+971%
|
| Forza Horizon 4 | 21−24
−991%
|
240−250
+991%
|
| Forza Horizon 5 | 12−14
−977%
|
140−150
+977%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
−1005%
|
210−220
+1005%
|
| Valorant | 60−65
−983%
|
650−700
+983%
|
Full HD
High
| Battlefield 5 | 20−22
−1000%
|
220−230
+1000%
|
| Counter-Strike 2 | 21−24
−995%
|
230−240
+995%
|
| Counter-Strike: Global Offensive | 96
−994%
|
1050−1100
+994%
|
| Cyberpunk 2077 | 10−11
−1000%
|
110−120
+1000%
|
| Dota 2 | 40−45
−998%
|
450−500
+998%
|
| Far Cry 5 | 14−16
−1033%
|
170−180
+1033%
|
| Fortnite | 27−30
−971%
|
300−310
+971%
|
| Forza Horizon 4 | 21−24
−991%
|
240−250
+991%
|
| Forza Horizon 5 | 12−14
−977%
|
140−150
+977%
|
| Grand Theft Auto V | 16−18
−1025%
|
180−190
+1025%
|
| Metro Exodus | 9−10
−1011%
|
100−105
+1011%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
−1005%
|
210−220
+1005%
|
| The Witcher 3: Wild Hunt | 14−16
−971%
|
150−160
+971%
|
| Valorant | 60−65
−983%
|
650−700
+983%
|
Full HD
Ultra
| Battlefield 5 | 20−22
−1000%
|
220−230
+1000%
|
| Cyberpunk 2077 | 10−11
−1000%
|
110−120
+1000%
|
| Dota 2 | 40−45
−998%
|
450−500
+998%
|
| Far Cry 5 | 14−16
−1033%
|
170−180
+1033%
|
| Forza Horizon 4 | 21−24
−991%
|
240−250
+991%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
−1005%
|
210−220
+1005%
|
| The Witcher 3: Wild Hunt | 14−16
−971%
|
150−160
+971%
|
| Valorant | 60−65
−983%
|
650−700
+983%
|
Full HD
Epic
| Fortnite | 27−30
−971%
|
300−310
+971%
|
1440p
High
| Counter-Strike 2 | 9−10
−1011%
|
100−105
+1011%
|
| Counter-Strike: Global Offensive | 35−40
−981%
|
400−450
+981%
|
| Grand Theft Auto V | 3−4
−900%
|
30−33
+900%
|
| Metro Exodus | 3−4
−900%
|
30−33
+900%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 35−40
−900%
|
350−400
+900%
|
| Valorant | 50−55
−958%
|
550−600
+958%
|
1440p
Ultra
| Battlefield 5 | 4−5
−1025%
|
45−50
+1025%
|
| Cyberpunk 2077 | 3−4
−900%
|
30−33
+900%
|
| Far Cry 5 | 9−10
−1011%
|
100−105
+1011%
|
| Forza Horizon 4 | 10−12
−991%
|
120−130
+991%
|
| The Witcher 3: Wild Hunt | 7−8
−971%
|
75−80
+971%
|
1440p
Epic
| Fortnite | 9−10
−1011%
|
100−105
+1011%
|
4K
High
| Grand Theft Auto V | 16−18
−1025%
|
180−190
+1025%
|
| The Witcher 3: Wild Hunt | 1−2
−900%
|
10−11
+900%
|
| Valorant | 24−27
−1025%
|
270−280
+1025%
|
4K
Ultra
| Battlefield 5 | 2−3
−950%
|
21−24
+950%
|
| Cyberpunk 2077 | 1−2
−900%
|
10−11
+900%
|
| Dota 2 | 16−18
−1025%
|
180−190
+1025%
|
| Far Cry 5 | 4−5
−1025%
|
45−50
+1025%
|
| Forza Horizon 4 | 6−7
−983%
|
65−70
+983%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 5−6
−1000%
|
55−60
+1000%
|
4K
Epic
| Fortnite | 5−6
−1000%
|
55−60
+1000%
|
This is how GTX 670MX and L40 compete in popular games:
- L40 is 1025% faster in 1080p
Pros & cons summary
| Performance score | 4.73 | 53.72 |
| Recency | 1 October 2012 | 13 October 2022 |
| Maximum RAM amount | 3 GB | 48 GB |
| Chip lithography | 28 nm | 4 nm |
| Power consumption (TDP) | 75 Watt | 300 Watt |
GTX 670MX has 300% lower power consumption.
L40, on the other hand, has a 1036% higher aggregate performance score, an age advantage of 10 years, a 1500% higher maximum VRAM amount, and a 600% more advanced lithography process.
The L40 is our recommended choice as it beats the GeForce GTX 670MX in performance tests.
Be aware that GeForce GTX 670MX is a notebook graphics card while L40 is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
