Quick/Comparisons
The Radeon RX 7900 XTX takes the lead in gaming performance with its higher score of 81, thanks to its excellent frame rates and efficient rendering capabilities.
The Radeon RX 7900 XTX edges out the GeForce RTX 4090 Laptop in content creation with a score of 75, leveraging its capable AI/ML compute and large memory pool.
Both GPUs show strong performance in AI/ML tasks, with the Radeon RX 7900 XTX scoring 74 and the GeForce RTX 4090 Laptop scoring 55, resulting in a close tie.
63 | Gaming | 81 |
63 | Workstation | 75 |
55 | AI/ML | 74 |
45 | Energy Efficiency | 43 |
59 | Quick Comparison Final Score | 77 |
| AD103 (GN21-X11) | Graphics Processor | Navi 31 |
| 9728 | Cores | 6144 |
| 304 / 112 | TMUs / ROPs | 384 / 192 |
| 7059.06 | Blender GPU | 4055.35 |
| 131 | Forza Horizon 5 | 174 |
| 182 | The Witcher 3 | 256 |
| 208 | Counter-Strike 2 | 232 |
| 147 | Far Cry 6 | 182 |
| 108 | Hogwarts Legacy | 137 |
| 164 | Call of Duty | 255 |
| 100 | Ghost of Tsushima | 138 |
| 137 | Cyberpunk 2077 | 181 |
| 231 | Tomb Raider | 277 |
| 156 | Average FPS | 204 |
| 187 | 1080p High | 241 |
| 156 | 1080p Ultra | 204 |
| 123 | 1440p Ultra | 159 |
| 72 | 4K Ultra | 94 |
| Low | Margin of Error | Low |
| 203263 | GB6 Compute Score | 224686 |
| 264 img/sec | Background Blur | 423.9 img/sec |
| 134.3 img/sec | Face Detection | 270.8 img/sec |
| 9.27 Gpixels/sec | Horizon Detection | 9.23 Gpixels/sec |
| 12.7 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 13.2 Gpixels/sec | Gaussian Blur | 11.1 Gpixels/sec |
| 1.92 Gpixels/sec | Feature Matching | 1.74 Gpixels/sec |
| 1060 Gpixels/sec | Stereo Matching | 871 Gpixels/sec |
| 29225.1 FPS | Particle Physics | 29891.2 FPS |
| OpenCL | API | OpenCL |
| 27060 | G3D Mark Score | 31406 |
| 988 | G2D Mark | 1285 |
| 258 FPS | DirectX 11 | 356 FPS |
| 106 FPS | DirectX 12 | 133 FPS |
| 12206 Ops/s | GPU Compute | 17768 Ops/s |
| 29362 | GB6 ML Single Precision | 42092 |
| 42611 | GB6 ML Half Precision | 50673 |
| 22212 | GB6 ML Quantized | 32874 |
| 11346 | Image Classification (SP) | 18608 |
| 24625 | Image Segmentation (HP) | 25385 |
| 36874 | Image Super Resolution (Q) | 45641 |
| 50088 | Face Detection (HP) | 71321 |
| 174844 | Pose Estimation (Q) | 257258 |
| 3226 | Text Classification (SP) | 5240 |
| 4905 | Machine Translation (HP) | 7425 |
| 14667 | Object Detection (SP) | 21335 |
| 53868 | Depth Estimation (Q) | 66140 |
| 340056 | Style Transfer (SP) | 483867 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 163-228 GPixel/s | Pixel Fill Rate | 480 GPixel/s |
| 442-620 GTexel/s | Texture Fill Rate | 959 GTexel/s |
| 28.3-39.7 TFLOPS | FLOPS (FP32) | 61.4 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 16 GB | Memory Size | 24 GB |
| 2000 MHz | Memory Clock | 2500 MHz |
| 16000 Mbps | Effective Memory Speed | 20000 Mbps |
| 256-bit | Bus | 384-bit |
| No | ECC | No |
| 512 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 80-175 W (configurable) | TGP | 355 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 379 mm² | Die Size | 529 mm² |
| 45.9 billion | Transistor Count | 57 billion |
| 121.11 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| February 8, 2023 | Released | November 3, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | RDNA 3.0 |
| AD103 (GN21-X11) | GPU Codename | Navi 31 |
| -Intel Core Ultra 9 185Hor above | Recommended CPU | -Intel Core i7 13700Kor above |
| 22501 | Steel Nomad Lite Score | 29870 |
| 21401 | Time Spy | 30766 |
| 96130 | Solar Bay | 123758 |
| 13733 | Port Royal | 16749 |
| 45218 | Fire Strike | 73217 |
| 42491 | Wild Life Extreme | 58530 |
| 147892 | Night Raid | 184767 |
| 930-1620 MHz (configurable) | Base Clock | 1929 MHz |
| 1455-2040 MHz (configurable) | Boost Clock | 2498 MHz |
| 9728 | Shading Units | 6144 |
| 304 | Texture Mapping Units (TMUs) | 384 |
| 112 | Render Output Units (ROPs) | 192 |
| 76 | Compute Units (Pipelines) | — |
| 304 | Tensor Cores | — |
| 76 | Ray-tracing Cores | 96 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 64MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |
Compare with something else?
Compare GeForce RTX 4090 with another →