Quick/Comparisons
9 | Gaming | 24 |
16 | Workstation | 29 |
11 | AI/ML |
Compare with something else?
Compare Radeon 680M with another →25 |
88 | Energy Efficiency | 60 |
24 | Quick Comparison Final Score | 31 |
| Rembrandt | Graphics Processor | Navi 23 |
| 768 | Cores | 1792 |
| 48 / 32 | TMUs / ROPs | 112 / 64 |
| 238.39 | Blender GPU | 904.6 |
| 19 | Forza Horizon 5 | 60 |
| 18 | The Witcher 3 | 81 |
| 26 | Counter-Strike 2 | 111 |
| 26 | Far Cry 6 | 75 |
| 13 | Hogwarts Legacy | 47 |
| 24 | Call of Duty | 71 |
| 13 | Ghost of Tsushima | 49 |
| 16 | Cyberpunk 2077 | 53 |
| 25 | Tomb Raider | 89 |
| 20 | Average FPS | 71 |
| 26 | 1080p High | 90 |
| 20 | 1080p Ultra | 71 |
| 13 | 1440p Ultra | 48 |
| - | 4K Ultra | 25 |
| Low | Margin of Error | Low |
| 28675 | GB6 Compute Score | 71125 |
| 73.8 img/sec | Background Blur | 176.1 img/sec |
| 30.1 img/sec | Face Detection | 102.4 img/sec |
| 0.93 Gpixels/sec | Horizon Detection | 2.19 Gpixels/sec |
| 1.17 Gpixels/sec | Edge Detection | 3.1 Gpixels/sec |
| 1.17 Gpixels/sec | Gaussian Blur | 2.8 Gpixels/sec |
| 0.37 Gpixels/sec | Feature Matching | 0.78 Gpixels/sec |
| 105 Gpixels/sec | Stereo Matching | 313.2 Gpixels/sec |
| 4640 FPS | Particle Physics | 8768.9 FPS |
| OpenCL | API | OpenCL |
| 4325 | G3D Mark Score | 13906 |
| 734 | G2D Mark | 724 |
| 39 FPS | DirectX 11 | 137 FPS |
| 20 FPS | DirectX 12 | 51 FPS |
| 1980 Ops/s | GPU Compute | 5593 Ops/s |
| 5834 | GB6 ML Single Precision | 14016 |
| 8202 | GB6 ML Half Precision | 16471 |
| 4169 | GB6 ML Quantized | 11065 |
| 1976 | Image Classification (SP) | 6355 |
| 3138 | Image Segmentation (HP) | 7183 |
| 6693 | Image Super Resolution (Q) | 16962 |
| 7213 | Face Detection (HP) | 20793 |
| 21849 | Pose Estimation (Q) | 65012 |
| 1497 | Text Classification (SP) | 2139 |
| 2579 | Machine Translation (HP) | 3411 |
| 2154 | Object Detection (SP) | 5102 |
| 9635 | Depth Estimation (Q) | 26194 |
| 56269 | Style Transfer (SP) | 139748 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 70-77 GPixel/s | Pixel Fill Rate | 97-139 GPixel/s |
| 106-115 GTexel/s | Texture Fill Rate | 170-244 GTexel/s |
| 3.4-3.7 TFLOPS | FLOPS (FP32) | 5.4-7.8 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| — | Memory Clock | 1750 MHz |
| — | Effective Memory Speed | 14000 Mbps |
| — | Bus | 128-bit |
| No | ECC | No |
| — | Memory Bandwidth | 224 GB/s |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x8 |
| 15 W | TGP | 50-100 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 6 nm | Fabrication Process | 7 nm |
| 208 mm² | Die Size | 237 mm² |
| 13.1 billion | Transistor Count | 11.06 billion |
| 62.98 MTr/mm² | Transistor Density | 46.67 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 2 | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 1.4 |
| Amd | Vendor | Amd |
| Integrated | Build | Discrete |
| January 1, 2022 | Released | June 1, 2021 |
| Laptop | Case | Laptop |
| Generic | Purpose | Gaming |
| Entry-level | Segment | Mid-range |
| RDNA 2.0 | Architecture | RDNA 2.0 |
| Rembrandt | GPU Codename | Navi 23 |
| -AMD Ryzen 7 6800Hor above | Recommended CPU | -AMD Ryzen 5 5600Hor above |
| 2141 | Steel Nomad Lite Score | 7012 |
| 2328 | Time Spy | 8011 |
| 9717 | Solar Bay | 30083 |
| 1010 | Port Royal | 3880 |
| 6897 | Fire Strike | 23175 |
| 4167 | Wild Life Extreme | 14422 |
| 27577 | Night Raid | 95245 |
| 400 MHz | Base Clock | 1489 MHz |
| 2200-2400 MHz (configurable) | Boost Clock | 1520-2177 MHz (configurable) |
| 768 | Shading Units | 1792 |
| 48 | Texture Mapping Units (TMUs) | 112 |
| 32 | Render Output Units (ROPs) | 64 |
| 12 | Compute Units (Pipelines) | 28 |
| — | Tensor Cores | — |
| 12 | Ray-tracing Cores | 28 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |