Quick/Comparisons
The Radeon RX 7900 XTX takes the lead in gaming performance with a score of 81, outpacing the GeForce RTX 3090 Ti's 66.
Both the GeForce RTX 3090 Ti and Radeon RX 7900 XTX deliver strong workstation performance, with scores of 73 and 75 respectively, making them a tie.
The Radeon RX 7900 XTX excels in AI/ML compute with a score of 74, surpassing the GeForce RTX 3090 Ti's 52.
66 | Gaming | 81 |
73 | Workstation | 75 |
52 | AI/ML | 74 |
37 | Energy Efficiency | 43 |
66 | Quick Comparison Final Score | 77 |
| GA102 | Graphics Processor | Navi 31 |
| 10752 | Cores | 6144 |
| 336 / 112 | TMUs / ROPs | 384 / 192 |
| 6057.83 | Blender GPU | 4055.35 |
| 141 | Forza Horizon 5 | 174 |
| 182 | The Witcher 3 | 256 |
| 210 | Counter-Strike 2 | 232 |
| 147 | Far Cry 6 | 182 |
| 112 | Hogwarts Legacy | 137 |
| 173 | Call of Duty | 255 |
| 108 | Ghost of Tsushima | 138 |
| 143 | Cyberpunk 2077 | 181 |
| 243 | Tomb Raider | 277 |
| 162 | Average FPS | 204 |
| 128 | 1440p Ultra | 159 |
| 75 | 4K Ultra | 94 |
| Low | Margin of Error | Low |
| 193 | 1080p High | 241 |
| 162 | 1080p Ultra | 204 |
| 232083 | GB6 Compute Score | 224686 |
| 362.7 img/sec | Background Blur | 423.9 img/sec |
| 227.9 img/sec | Face Detection | 270.8 img/sec |
| 11.3 Gpixels/sec | Horizon Detection | 9.23 Gpixels/sec |
| 15.9 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 12.1 Gpixels/sec | Gaussian Blur | 11.1 Gpixels/sec |
| 1.56 Gpixels/sec | Feature Matching | 1.74 Gpixels/sec |
| 1080 Gpixels/sec | Stereo Matching | 871 Gpixels/sec |
| 31024.6 FPS | Particle Physics | 29891.2 FPS |
| OpenCL | API | OpenCL |
| 29288 | G3D Mark Score | 31406 |
| 1226 | G2D Mark | 1285 |
| 238 FPS | DirectX 11 | 356 FPS |
| 122 FPS | DirectX 12 | 133 FPS |
| 16569 Ops/s | GPU Compute | 17768 Ops/s |
| 26701 | GB6 ML Single Precision | 42092 |
| 38573 | GB6 ML Half Precision | 50673 |
| 15995 | GB6 ML Quantized | 32874 |
| 10246 | Image Classification (SP) | 18608 |
| 22830 | Image Segmentation (HP) | 25385 |
| 23532 | Image Super Resolution (Q) | 45641 |
| 48657 | Face Detection (HP) | 71321 |
| 147241 | Pose Estimation (Q) | 257258 |
| 2917 | Text Classification (SP) | 5240 |
| 4427 | Machine Translation (HP) | 7425 |
| 13323 | Object Detection (SP) | 21335 |
| 40055 | Depth Estimation (Q) | 66140 |
| 298683 | Style Transfer (SP) | 483867 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 208 GPixel/s | Pixel Fill Rate | 480 GPixel/s |
| 625 GTexel/s | Texture Fill Rate | 959 GTexel/s |
| 40 TFLOPS | FLOPS (FP32) | 61.4 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 24 GB | Memory Size | 24 GB |
| 1313 MHz | Memory Clock | 2500 MHz |
| 21000 Mbps | Effective Memory Speed | 20000 Mbps |
| 384-bit | Bus | 384-bit |
| No | ECC | No |
| 1008 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 450 W | TGP | 355 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 628 mm² | Die Size | 529 mm² |
| 28 billion | Transistor Count | 57 billion |
| 44.59 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 |
| 8.6 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| March 29, 2022 | Released | November 3, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | RDNA 3.0 |
| GA102 | GPU Codename | Navi 31 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core i7 13700Kor above |
| 24378 | Steel Nomad Lite Score | 29870 |
| 21854 | Time Spy | 30766 |
| 109167 | Solar Bay | 123758 |
| 14888 | Port Royal | 16749 |
| 51943 | Fire Strike | 73217 |
| 48864 | Wild Life Extreme | 58530 |
| 156500 | Night Raid | 184767 |
| 1560 MHz | Base Clock | 1929 MHz |
| 1860 MHz | Boost Clock | 2498 MHz |
| 10752 | Shading Units | 6144 |
| 336 | Texture Mapping Units (TMUs) | 384 |
| 112 | Render Output Units (ROPs) | 192 |
| 84 | Compute Units (Pipelines) | — |
| 336 | Tensor Cores | — |
| 84 | Ray-tracing Cores | 96 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 6MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |
Compare with something else?
Compare GeForce RTX 3090 with another →