L40S vs GeForce RTX 4090
Aggregate performance score
We've compared GeForce RTX 4090 with L40S, including specs and performance data.
RTX 4090 outperforms L40S by an impressive 91% 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 | 3 | 77 |
| Place by popularity | 90 | not in top-100 |
| Cost-effectiveness evaluation | 30.74 | no data |
| Power efficiency | 15.44 | 12.15 |
| Architecture | Ada Lovelace (2022−2024) | Ada Lovelace (2022−2024) |
| GPU code name | AD102 | AD102 |
| Market segment | Desktop | Workstation |
| Release date | 20 September 2022 (2 years ago) | 13 October 2022 (2 years ago) |
| Launch price (MSRP) | $1,599 | no data |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
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 | 16384 | 18176 |
| Core clock speed | 2235 MHz | 1110 MHz |
| Boost clock speed | 2520 MHz | 2520 MHz |
| Number of transistors | 76,300 million | 76,300 million |
| Manufacturing process technology | 5 nm | 5 nm |
| Power consumption (TDP) | 450 Watt | 300 Watt |
| Texture fill rate | 1,290 | 1,431 |
| Floating-point processing power | 82.58 TFLOPS | 91.61 TFLOPS |
| ROPs | 176 | 192 |
| TMUs | 512 | 568 |
| Tensor Cores | 512 | 568 |
| Ray Tracing Cores | 128 | 142 |
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).
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Length | 304 mm | 267 mm |
| Width | 3-slot | 2-slot |
| Supplementary power connectors | 1x 16-pin | 1x 16-pin |
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 | GDDR6X | GDDR6 |
| Maximum RAM amount | 24 GB | 48 GB |
| Memory bus width | 384 Bit | 384 Bit |
| Memory clock speed | 1313 MHz | 2250 MHz |
| Memory bandwidth | 1.01 TB/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 | 1x HDMI 2.1, 3x DisplayPort 1.4a | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| HDMI | + | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.8 | 6.7 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 8.9 | 8.9 |
| DLSS | + | + |
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.
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.
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 | 252
+93.8%
| 130−140
−93.8%
|
| 1440p | 191
+91%
| 100−110
−91%
|
| 4K | 139
+98.6%
| 70−75
−98.6%
|
Cost per frame, $
| 1080p | 6.35 | no data |
| 1440p | 8.37 | no data |
| 4K | 11.50 | no data |
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 351
+95%
|
180−190
−95%
|
| Cyberpunk 2077 | 227
+106%
|
110−120
−106%
|
| God of War | 246
+105%
|
120−130
−105%
|
Full HD
Medium Preset
| Battlefield 5 | 190−200
+97%
|
100−105
−97%
|
| Counter-Strike 2 | 340
+100%
|
170−180
−100%
|
| Cyberpunk 2077 | 224
+104%
|
110−120
−104%
|
| Far Cry 5 | 209
+109%
|
100−105
−109%
|
| Fortnite | 300−350
+101%
|
150−160
−101%
|
| Forza Horizon 4 | 300−350
+91.1%
|
180−190
−91.1%
|
| Forza Horizon 5 | 281
+101%
|
140−150
−101%
|
| God of War | 245
+104%
|
120−130
−104%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+94.4%
|
90−95
−94.4%
|
| Valorant | 650−700
+94.3%
|
350−400
−94.3%
|
Full HD
High Preset
| Battlefield 5 | 190−200
+97%
|
100−105
−97%
|
| Counter-Strike 2 | 340
+100%
|
170−180
−100%
|
| Counter-Strike: Global Offensive | 270−280
+98.6%
|
140−150
−98.6%
|
| Cyberpunk 2077 | 215
+95.5%
|
110−120
−95.5%
|
| Dota 2 | 253
+94.6%
|
130−140
−94.6%
|
| Far Cry 5 | 201
+101%
|
100−105
−101%
|
| Fortnite | 300−350
+101%
|
150−160
−101%
|
| Forza Horizon 4 | 300−350
+91.1%
|
180−190
−91.1%
|
| Forza Horizon 5 | 275
+96.4%
|
140−150
−96.4%
|
| God of War | 243
+103%
|
120−130
−103%
|
| Grand Theft Auto V | 174
+93.3%
|
90−95
−93.3%
|
| Metro Exodus | 228
+107%
|
110−120
−107%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+94.4%
|
90−95
−94.4%
|
| The Witcher 3: Wild Hunt | 573
+91%
|
300−310
−91%
|
| Valorant | 650−700
+94.3%
|
350−400
−94.3%
|
Full HD
Ultra Preset
| Battlefield 5 | 190−200
+97%
|
100−105
−97%
|
| Cyberpunk 2077 | 211
+91.8%
|
110−120
−91.8%
|
| Dota 2 | 224
+104%
|
110−120
−104%
|
| Far Cry 5 | 187
+96.8%
|
95−100
−96.8%
|
| Forza Horizon 4 | 300−350
+91.1%
|
180−190
−91.1%
|
| God of War | 206
+106%
|
100−105
−106%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+94.4%
|
90−95
−94.4%
|
| The Witcher 3: Wild Hunt | 304
+103%
|
150−160
−103%
|
| Valorant | 680
+94.3%
|
350−400
−94.3%
|
Full HD
Epic Preset
| Fortnite | 300−350
+101%
|
150−160
−101%
|
1440p
High Preset
| Counter-Strike 2 | 312
+95%
|
160−170
−95%
|
| Counter-Strike: Global Offensive | 500−550
+91.1%
|
270−280
−91.1%
|
| Grand Theft Auto V | 162
+103%
|
80−85
−103%
|
| Metro Exodus | 179
+98.9%
|
90−95
−98.9%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+94.4%
|
90−95
−94.4%
|
| Valorant | 450−500
+94%
|
250−260
−94%
|
1440p
Ultra Preset
| Battlefield 5 | 190−200
+96%
|
100−105
−96%
|
| Cyberpunk 2077 | 159
+98.8%
|
80−85
−98.8%
|
| Far Cry 5 | 186
+95.8%
|
95−100
−95.8%
|
| Forza Horizon 4 | 300−350
+91.3%
|
160−170
−91.3%
|
| God of War | 180
+100%
|
90−95
−100%
|
| The Witcher 3: Wild Hunt | 259
+99.2%
|
130−140
−99.2%
|
1440p
Epic Preset
| Fortnite | 150−160
+101%
|
75−80
−101%
|
4K
High Preset
| Counter-Strike 2 | 166
+95.3%
|
85−90
−95.3%
|
| Grand Theft Auto V | 187
+96.8%
|
95−100
−96.8%
|
| Metro Exodus | 136
+94.3%
|
70−75
−94.3%
|
| The Witcher 3: Wild Hunt | 280
+100%
|
140−150
−100%
|
| Valorant | 300−350
+94.7%
|
170−180
−94.7%
|
4K
Ultra Preset
| Battlefield 5 | 130−140
+94.3%
|
70−75
−94.3%
|
| Counter-Strike 2 | 140−150
+97.3%
|
75−80
−97.3%
|
| Cyberpunk 2077 | 81
+103%
|
40−45
−103%
|
| Dota 2 | 227
+106%
|
110−120
−106%
|
| Far Cry 5 | 169
+98.8%
|
85−90
−98.8%
|
| Forza Horizon 4 | 300−350
+103%
|
150−160
−103%
|
| God of War | 127
+95.4%
|
65−70
−95.4%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+92%
|
50−55
−92%
|
4K
Epic Preset
| Fortnite | 75−80
+97.5%
|
40−45
−97.5%
|
This is how RTX 4090 and L40S compete in popular games:
- RTX 4090 is 94% faster in 1080p
- RTX 4090 is 91% faster in 1440p
- RTX 4090 is 99% faster in 4K
Pros & cons summary
| Performance score | 91.13 | 47.78 |
| Maximum RAM amount | 24 GB | 48 GB |
| Power consumption (TDP) | 450 Watt | 300 Watt |
RTX 4090 has a 90.7% higher aggregate performance score.
L40S, on the other hand, has a 100% higher maximum VRAM amount, and 50% lower power consumption.
The GeForce RTX 4090 is our recommended choice as it beats the L40S in performance tests.
Be aware that GeForce RTX 4090 is a desktop graphics card while L40S 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.
