Quick/Comparisons
The Radeon RX 7900 XTX's superior gaming performance makes it the clear winner, with a score of 81 compared to the Radeon RX 6500M's 14.
The Radeon RX 7900 XTX's higher workstation score of 75 gives it the edge over the Radeon RX 6500M's 21, making it the winner in this use case.
The Radeon RX 7900 XTX's strong AI/ML compute capabilities, with a score of 74, make it the winner in this use case, outperforming the Radeon RX 6500M's 14.
14 | Gaming | 81 |
21 | Workstation | 75 |
14 | AI/ML | 74 |
78 | Energy Efficiency | 43 |
27 | Quick Comparison Final Score | 77 |
| Navi 24 | Graphics Processor | Navi 31 |
| 1024 | Cores | 6144 |
| 64 / 32 | TMUs / ROPs | 384 / 192 |
| 384.34 | Blender GPU | 4055.35 |
| 36 | Forza Horizon 5 | 174 |
| 38 | The Witcher 3 | 256 |
| 45 | Counter-Strike 2 | 232 |
| 44 | Far Cry 6 | 182 |
| 24 | Hogwarts Legacy | 137 |
| 39 | Call of Duty | 255 |
| 19 | Ghost of Tsushima | 138 |
| 27 | Cyberpunk 2077 | 181 |
| 46 | Tomb Raider | 277 |
| 35 | Average FPS | 204 |
| 46 | 1080p High | 241 |
| 35 | 1080p Ultra | 204 |
| 23 | 1440p Ultra | 159 |
| 12 | 4K Ultra | 94 |
| Low | Margin of Error | Low |
| 46706 | GB6 Compute Score | 224686 |
| 112.4 img/sec | Background Blur | 423.9 img/sec |
| 61.7 img/sec | Face Detection | 270.8 img/sec |
| 1.49 Gpixels/sec | Horizon Detection | 9.23 Gpixels/sec |
| 2.01 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 1.81 Gpixels/sec | Gaussian Blur | 11.1 Gpixels/sec |
| 0.58 Gpixels/sec | Feature Matching | 1.74 Gpixels/sec |
| 183 Gpixels/sec | Stereo Matching | 871 Gpixels/sec |
| 6313.2 FPS | Particle Physics | 29891.2 FPS |
| OpenCL | API | OpenCL |
| 7346 | G3D Mark Score | 31406 |
| 371 | G2D Mark | 1285 |
| 69 FPS | DirectX 11 | 356 FPS |
| 33 FPS | DirectX 12 | 133 FPS |
| 2545 Ops/s | GPU Compute | 17768 Ops/s |
| 8067 | GB6 ML Single Precision | 42092 |
| 9896 | GB6 ML Half Precision | 50673 |
| 5967 | GB6 ML Quantized | 32874 |
| 2972 | Image Classification (SP) | 18608 |
| 4132 | Image Segmentation (HP) | 25385 |
| 9120 | Image Super Resolution (Q) | 45641 |
| 11506 | Face Detection (HP) | 71321 |
| 35378 | Pose Estimation (Q) | 257258 |
| 1536 | Text Classification (SP) | 5240 |
| 1869 | Machine Translation (HP) | 7425 |
| 3259 | Object Detection (SP) | 21335 |
| 11922 | Depth Estimation (Q) | 66140 |
| 81312 | Style Transfer (SP) | 483867 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 70 GPixel/s | Pixel Fill Rate | 480 GPixel/s |
| 140 GTexel/s | Texture Fill Rate | 959 GTexel/s |
| 4.5 TFLOPS | FLOPS (FP32) | 61.4 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 4 GB | Memory Size | 24 GB |
| 2000 MHz | Memory Clock | 2500 MHz |
| 16000 Mbps | Effective Memory Speed | 20000 Mbps |
| 64-bit | Bus | 384-bit |
| No | ECC | No |
| 128 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 4.0 x4 | Interface | PCIe 4.0 x16 |
| 50 W | TGP | 355 W |
| TSMC | Manufacturing | TSMC |
| 6 nm | Fabrication Process | 5 nm |
| 107 mm² | Die Size | 529 mm² |
| 5.4 billion | Transistor Count | 57 billion |
| 50.47 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2.2 | OpenCL | 2.2 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4 | DisplayPort | 2.1 |
| Amd | Vendor | Amd |
| Discrete | Build | Discrete |
| January 4, 2022 | Released | November 3, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | High-end |
| RDNA 2.0 | Architecture | RDNA 3.0 |
| Navi 24 | GPU Codename | Navi 31 |
| -AMD Ryzen 5 6600Hor above | Recommended CPU | -Intel Core i7 13700Kor above |
| 3850 | Steel Nomad Lite Score | 29870 |
| 3831 | Time Spy | 30766 |
| 15034 | Solar Bay | 123758 |
| 248 | Port Royal | 16749 |
| 12343 | Fire Strike | 73217 |
| 8150 | Wild Life Extreme | 58530 |
| 45550 | Night Raid | 184767 |
| 2000 MHz | Base Clock | 1929 MHz |
| 2190 MHz | Boost Clock | 2498 MHz |
| 1024 | Shading Units | 6144 |
| 64 | Texture Mapping Units (TMUs) | 384 |
| 32 | Render Output Units (ROPs) | 192 |
| 16 | Compute Units (Pipelines) | — |
| — | Tensor Cores | — |
| 16 | Ray-tracing Cores | 96 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 1MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |
Compare with something else?
Compare Radeon RX 6500M with another →