Quick/Comparisons
9 | Gaming | 5 |
16 | Workstation | 11 |
11 | AI/ML |
Compare with something else?
Compare Radeon 680M with another →4 |
88 | Energy Efficiency | 89 |
24 | Quick Comparison Final Score | 20 |
| Rembrandt | Graphics Processor | Raphael |
| 768 | Cores | 128 |
| 48 / 32 | TMUs / ROPs | 8 / 4 |
| 238.39 | Blender GPU | — |
| 19 | Forza Horizon 5 | — |
| 18 | The Witcher 3 | — |
| 26 | Counter-Strike 2 | — |
| 26 | Far Cry 6 | — |
| 13 | Hogwarts Legacy | — |
| 24 | Call of Duty | — |
| 13 | Ghost of Tsushima | — |
| 16 | Cyberpunk 2077 | — |
| 25 | Tomb Raider | — |
| 20 | Average FPS | — |
| 26 | 1080p High | — |
| 20 | 1080p Ultra | — |
| 13 | 1440p Ultra | — |
| - | 4K Ultra | — |
| Low | Margin of Error | — |
| 28675 | GB6 Compute Score | 6272 |
| 73.8 img/sec | Background Blur | 13.4 img/sec |
| 30.1 img/sec | Face Detection | 8.66 img/sec |
| 0.93 Gpixels/sec | Horizon Detection | 0.23 Gpixels/sec |
| 1.17 Gpixels/sec | Edge Detection | 0.32 Gpixels/sec |
| 1.17 Gpixels/sec | Gaussian Blur | 0.2 Gpixels/sec |
| 0.37 Gpixels/sec | Feature Matching | 0.08 Gpixels/sec |
| 105 Gpixels/sec | Stereo Matching | 24.2 Gpixels/sec |
| 4640 FPS | Particle Physics | 827 FPS |
| OpenCL | API | OpenCL |
| 4325 | G3D Mark Score | 1757 |
| 734 | G2D Mark | 516 |
| 39 FPS | DirectX 11 | 15 FPS |
| 20 FPS | DirectX 12 | 7 FPS |
| 1980 Ops/s | GPU Compute | 1128 Ops/s |
| 5834 | GB6 ML Single Precision | 1965 |
| 8202 | GB6 ML Half Precision | 2172 |
| 4169 | GB6 ML Quantized | 1610 |
| 1976 | Image Classification (SP) | 679 |
| 3138 | Image Segmentation (HP) | 642 |
| 6693 | Image Super Resolution (Q) | 2131 |
| 7213 | Face Detection (HP) | 2204 |
| 21849 | Pose Estimation (Q) | 5478 |
| 1497 | Text Classification (SP) | 728 |
| 2579 | Machine Translation (HP) | 1231 |
| 2154 | Object Detection (SP) | 729 |
| 9635 | Depth Estimation (Q) | 3337 |
| 56269 | Style Transfer (SP) | 11335 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 70-77 GPixel/s | Pixel Fill Rate | 9 GPixel/s |
| 106-115 GTexel/s | Texture Fill Rate | 18 GTexel/s |
| 3.4-3.7 TFLOPS | FLOPS (FP32) | 0.6 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| — | Memory Clock | — |
| — | Effective Memory Speed | — |
| — | Bus | — |
| No | ECC | No |
| — | Memory Bandwidth | — |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x8 |
| 15 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 6 nm | Fabrication Process | 6 nm |
| 208 mm² | Die Size | 122 mm² |
| 13.1 billion | Transistor Count | 3.4 billion |
| 62.98 MTr/mm² | Transistor Density | 27.87 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2 | OpenCL | 2 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | — |
| Amd | Vendor | Amd |
| Integrated | Build | Integrated |
| January 1, 2022 | Released | October 1, 2022 |
| Laptop | Case | Laptop |
| Generic | Purpose | Generic |
| Entry-level | Segment | Entry-level |
| RDNA 2.0 | Architecture | RDNA 2.0 |
| Rembrandt | GPU Codename | Raphael |
| -AMD Ryzen 7 6800Hor above | Recommended CPU | -AMD Ryzen 5 7600or above |
| 2141 | Steel Nomad Lite Score | 616 |
| 2328 | Time Spy | 711 |
| 9717 | Solar Bay | 2913 |
| 1010 | Port Royal | 332 |
| 6897 | Fire Strike | 2417 |
| 4167 | Wild Life Extreme | 1402 |
| 27577 | Night Raid | 10038 |
| 400 MHz | Base Clock | 400 MHz |
| 2200-2400 MHz (configurable) | Boost Clock | 2200 MHz |
| 768 | Shading Units | 128 |
| 48 | Texture Mapping Units (TMUs) | 8 |
| 32 | Render Output Units (ROPs) | 4 |
| 12 | Compute Units (Pipelines) | 2 |
| — | Tensor Cores | — |
| 12 | Ray-tracing Cores | 2 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |