Quick/Comparisons
54 | Gaming | 5 |
55 | Workstation | 13 |
45 | AI/ML |
Compare with something else?
Compare Radeon RX 7900M with another →6 |
45 | Energy Efficiency | 75 |
52 | Quick Comparison Final Score | 19 |
| Navi 31 | Graphics Processor | — |
| 4608 | Cores | 448 |
| 288 / 192 | TMUs / ROPs | 28 / 8 |
| 2436.73 | Blender GPU | — |
| 129 | Forza Horizon 5 | 10 |
| 164 | The Witcher 3 | — |
| 197 | Counter-Strike 2 | 14 |
| 140 | Far Cry 6 | 11 |
| 96 | Hogwarts Legacy | - |
| 151 | Call of Duty | 13 |
| 96 | Ghost of Tsushima | - |
| 109 | Cyberpunk 2077 | - |
| 182 | Tomb Raider | 11 |
| 140 | Average FPS | 10 |
| 171 | 1080p High | 13 |
| 140 | 1080p Ultra | 10 |
| 107 | 1440p Ultra | - |
| 63 | 4K Ultra | - |
| High | Margin of Error | Low |
| 151924 | GB6 Compute Score | 14408 |
| 305.8 img/sec | Background Blur | 33.7 img/sec |
| 201.4 img/sec | Face Detection | 15.4 img/sec |
| 5.87 Gpixels/sec | Horizon Detection | 0.35 Gpixels/sec |
| 8.19 Gpixels/sec | Edge Detection | 0.76 Gpixels/sec |
| 6.77 Gpixels/sec | Gaussian Blur | 0.69 Gpixels/sec |
| 1.32 Gpixels/sec | Feature Matching | 0.21 Gpixels/sec |
| 540.4 Gpixels/sec | Stereo Matching | 54.7 Gpixels/sec |
| 22269 FPS | Particle Physics | 1957.6 FPS |
| OpenCL | API | OpenCL |
| 22111 | G3D Mark Score | 2250 |
| 893 | G2D Mark | 568 |
| 256 FPS | DirectX 11 | 16 FPS |
| 96 FPS | DirectX 12 | 11 FPS |
| 9043 Ops/s | GPU Compute | 1215 Ops/s |
| 25398 | GB6 ML Single Precision | 3157 |
| 28752 | GB6 ML Half Precision | 4191 |
| 19862 | GB6 ML Quantized | 2365 |
| 11249 | Image Classification (SP) | 1323 |
| 13771 | Image Segmentation (HP) | 1675 |
| 30143 | Image Super Resolution (Q) | 2919 |
| 31918 | Face Detection (HP) | 4386 |
| 163344 | Pose Estimation (Q) | 9348 |
| 3882 | Text Classification (SP) | 1024 |
| 3734 | Machine Translation (HP) | 1888 |
| 12629 | Object Detection (SP) | 1452 |
| 45969 | Depth Estimation (Q) | 5272 |
| 303544 | Style Transfer (SP) | 19585 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 401 GPixel/s | Pixel Fill Rate | 12-16 GPixel/s |
| 602 GTexel/s | Texture Fill Rate | 42-56 GTexel/s |
| 38.5 TFLOPS | FLOPS (FP32) | 1.3-1.8 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 16 GB | Memory Size | System RAM Dependent |
| 2250 MHz | Memory Clock | System RAM Dependent |
| 18000 Mbps | Effective Memory Speed | System RAM Dependent |
| 256-bit | Bus | — |
| No | ECC | No |
| 576 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | IGP |
| 180 W | TGP | 10-45 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 7 nm |
| 529 mm² | Die Size | — |
| 57.7 billion | Transistor Count | — |
| 109.07 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.1 |
| 1.3 | Vulkan | — |
| 4.6 | OpenGL | 4.6 |
| 2.2 | OpenCL | 2.2 |
| — | CUDA | — |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | — |
| Amd | Vendor | Amd |
| Discrete | Build | Integrated |
| October 19, 2023 | Released | January 7, 2020 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| RDNA 3.0 | Architecture | Raven |
| Navi 31 | GPU Codename | — |
| -Intel Core i7 13700HXor above | Recommended CPU | -AMD Ryzen 5 5500Uor above |
| 17147 | Steel Nomad Lite Score | 943 |
| 18071 | Time Spy | 1068 |
| 77397 | Solar Bay | — |
| 10145 | Port Royal | — |
| 44044 | Fire Strike | 3396 |
| 35258 | Wild Life Extreme | 2015 |
| 153739 | Night Raid | 13093 |
| 192 | Render Output Units (ROPs) | 8 |
| — | Compute Units (Pipelines) | 7 |
| — | Tensor Cores | No |
| 72 | Ray-tracing Cores | No |
| 256KB per cluster | L1 Cache | — |
| 6MB shared | L2 Cache | — |
| 4 IPC | Instructions Per Cycle | 2 IPC |
| 1825 MHz | Base Clock | 300 MHz |
| 2090 MHz | Boost Clock | 1500-2000 MHz (configurable) |
| 4608 | Shading Units | 448 |
| 288 | Texture Mapping Units (TMUs) | 28 |