Quick/Comparisons
9 | Gaming | 14 |
16 | Workstation | 17 |
11 | AI/ML |
Compare with something else?
Compare Radeon 680M with another →6 |
88 | Energy Efficiency | 64 |
24 | Quick Comparison Final Score | 22 |
| Rembrandt | Graphics Processor | Navi 14 |
| 768 | Cores | 1280 |
| 48 / 32 | TMUs / ROPs | 80 / 32 |
| 238.39 | Blender GPU | 238.18 |
| 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 | 27065 |
| 73.8 img/sec | Background Blur | 59.6 img/sec |
| 30.1 img/sec | Face Detection | 34.3 img/sec |
| 0.93 Gpixels/sec | Horizon Detection | 1.19 Gpixels/sec |
| 1.17 Gpixels/sec | Edge Detection | 1.56 Gpixels/sec |
| 1.17 Gpixels/sec | Gaussian Blur | 1.31 Gpixels/sec |
| 0.37 Gpixels/sec | Feature Matching | 0.28 Gpixels/sec |
| 105 Gpixels/sec | Stereo Matching | 95.4 Gpixels/sec |
| 4640 FPS | Particle Physics | 2473.3 FPS |
| OpenCL | API | OpenCL |
| 4325 | G3D Mark Score | 5812 |
| 734 | G2D Mark | 559 |
| 39 FPS | DirectX 11 | 36 FPS |
| 20 FPS | DirectX 12 | 25 FPS |
| 1980 Ops/s | GPU Compute | 2580 Ops/s |
| 5834 | GB6 ML Single Precision | 3321 |
| 8202 | GB6 ML Half Precision | 3307 |
| 4169 | GB6 ML Quantized | 1043 |
| 1976 | Image Classification (SP) | 2457 |
| 3138 | Image Segmentation (HP) | 394 |
| 6693 | Image Super Resolution (Q) | 6055 |
| 7213 | Face Detection (HP) | 9021 |
| 21849 | Pose Estimation (Q) | 2239 |
| 1497 | Text Classification (SP) | 344 |
| 2579 | Machine Translation (HP) | 458 |
| 2154 | Object Detection (SP) | 2523 |
| 9635 | Depth Estimation (Q) | 10775 |
| 56269 | Style Transfer (SP) | 30282 |
| ONNX | Framework | Core ML |
| DirectML | Backend | GPU |
| 70-77 GPixel/s | Pixel Fill Rate | 40 GPixel/s |
| 106-115 GTexel/s | Texture Fill Rate | 100 GTexel/s |
| 3.4-3.7 TFLOPS | FLOPS (FP32) | 3.2 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 4 GB |
| — | Memory Clock | 1500 MHz |
| — | Effective Memory Speed | 12000 Mbps |
| — | Bus | 128-bit |
| No | ECC | — |
| — | Memory Bandwidth | 192 GB/s |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x8 |
| 15 W | TGP | 85 W |
| TSMC | Manufacturing | TSMC |
| 6 nm | Fabrication Process | 7 nm |
| 208 mm² | Die Size | 158 mm² |
| 13.1 billion | Transistor Count | 6.4 billion |
| 62.98 MTr/mm² | Transistor Density | 40.51 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 2 | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | 1.4 |
| Amd | Vendor | Amd |
| Integrated | Build | Discrete |
| January 1, 2022 | Released | November 13, 2019 |
| Laptop | Case | Laptop |
| Generic | Purpose | Gaming |
| Entry-level | Segment | Mid-range |
| RDNA 2.0 | Architecture | RDNA 1.0 |
| Rembrandt | GPU Codename | Navi 14 |
| -AMD Ryzen 7 6800Hor above | Recommended CPU | — |
| 2141 | Steel Nomad Lite Score | — |
| 2328 | Time Spy | 3404 |
| 9717 | Solar Bay | — |
| 1010 | Port Royal | — |
| 6897 | Fire Strike | — |
| 4167 | Wild Life Extreme | — |
| 27577 | Night Raid | — |
| 400 MHz | Base Clock | 1000 MHz |
| 2200-2400 MHz (configurable) | Boost Clock | 1250 MHz |
| 768 | Shading Units | 1280 |
| 48 | Texture Mapping Units (TMUs) | 80 |
| 32 | Render Output Units (ROPs) | 32 |
| 12 | Compute Units (Pipelines) | 20 |
| — | Tensor Cores | No |
| 12 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 2MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |