Quick/Comparisons
The Radeon RX 7900 XTX takes the lead with an 81 score, thanks to its superior performance in demanding games. Its 28-point gap over the Radeon RX 6800 XT is a significant advantage.
The Radeon RX 7900 XTX edges out the Radeon RX 6800 XT with a 25-point gap, offering better performance in content creation workloads. Its RDNA 3.0 architecture provides a notable boost.
The Radeon RX 7900 XTX takes the lead in AI/ML workloads with a 23-point gap, thanks to its capable compute performance and large memory pool. Its 24GB GDDR6 memory provides ample resources for demanding tasks.
53 | Gaming | 81 |
50 | Workstation | 75 |
51 | AI/ML |
Compare with something else?
Compare Radeon RX 6800 with another →74 |
36 | Energy Efficiency | 43 |
51 | Quick Comparison Final Score | 77 |
| Navi 21 | Graphics Processor | Navi 31 |
| 4608 | Cores | 6144 |
| 288 / 128 | TMUs / ROPs | 384 / 192 |
| 2413.97 | Blender GPU | 4055.35 |
| 132 | Forza Horizon 5 | 174 |
| 175 | The Witcher 3 | 256 |
| 201 | Counter-Strike 2 | 232 |
| 139 | Far Cry 6 | 182 |
| 97 | Hogwarts Legacy | 137 |
| 161 | Call of Duty | 255 |
| 103 | Ghost of Tsushima | 138 |
| 118 | Cyberpunk 2077 | 181 |
| 190 | Tomb Raider | 277 |
| 146 | Average FPS | 204 |
| 178 | 1080p High | 241 |
| 146 | 1080p Ultra | 204 |
| 112 | 1440p Ultra | 159 |
| 64 | 4K Ultra | 94 |
| Low | Margin of Error | Low |
| 138858 | GB6 Compute Score | 224686 |
| 335.7 img/sec | Background Blur | 423.9 img/sec |
| 221.1 img/sec | Face Detection | 270.8 img/sec |
| 6.16 Gpixels/sec | Horizon Detection | 9.23 Gpixels/sec |
| 8.96 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 7.44 Gpixels/sec | Gaussian Blur | 11.1 Gpixels/sec |
| 1.31 Gpixels/sec | Feature Matching | 1.74 Gpixels/sec |
| 263 Gpixels/sec | Stereo Matching | 871 Gpixels/sec |
| 14755 FPS | Particle Physics | 29891.2 FPS |
| OpenCL | API | OpenCL |
| 25040 | G3D Mark Score | 31406 |
| 1043 | G2D Mark | 1285 |
| 265 FPS | DirectX 11 | 356 FPS |
| 99 FPS | DirectX 12 | 133 FPS |
| 13129 Ops/s | GPU Compute | 17768 Ops/s |
| 30220 | GB6 ML Single Precision | 42092 |
| 30423 | GB6 ML Half Precision | 50673 |
| 22583 | GB6 ML Quantized | 32874 |
| 11942 | Image Classification (SP) | 18608 |
| 7603 | Image Segmentation (HP) | 25385 |
| 30511 | Image Super Resolution (Q) | 45641 |
| 42862 | Face Detection (HP) | 71321 |
| 160019 | Pose Estimation (Q) | 257258 |
| 4247 | Text Classification (SP) | 5240 |
| 6279 | Machine Translation (HP) | 7425 |
| 13910 | Object Detection (SP) | 21335 |
| 51794 | Depth Estimation (Q) | 66140 |
| 324124 | Style Transfer (SP) | 483867 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 288 GPixel/s | Pixel Fill Rate | 480 GPixel/s |
| 648 GTexel/s | Texture Fill Rate | 959 GTexel/s |
| 20.7 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 |
| 300 W | TGP | 355 W |
| TSMC | Manufacturing | TSMC |
| 7 nm | Fabrication Process | 5 nm |
| 520 mm² | Die Size | 529 mm² |
| 26 billion | Transistor Count | 57 billion |
| 50 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 2.2 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Amd | Vendor | Amd |
| Discrete | Build | Discrete |
| November 18, 2020 | Released | November 3, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| RDNA 2.0 | Architecture | RDNA 3.0 |
| Navi 21 | GPU Codename | Navi 31 |
| -Intel Core i7 12700Kor above | Recommended CPU | -Intel Core i7 13700Kor above |
| 17589 | Steel Nomad Lite Score | 29870 |
| 19370 | Time Spy | 30766 |
| 78731 | Solar Bay | 123758 |
| 9712 | Port Royal | 16749 |
| 53016 | Fire Strike | 73217 |
| 35632 | Wild Life Extreme | 58530 |
| 155398 | Night Raid | 184767 |
| 1825 MHz | Base Clock | 1929 MHz |
| 2250 MHz | Boost Clock | 2498 MHz |
| 4608 | Shading Units | 6144 |
| 288 | Texture Mapping Units (TMUs) | 384 |
| 128 | Render Output Units (ROPs) | 192 |
| — | Compute Units (Pipelines) | — |
| — | Tensor Cores | — |
| 72 | Ray-tracing Cores | 96 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 4MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |