Quick/Comparisons
10 | Gaming | 6 |
15 | Workstation | 9 |
17 | AI/ML |
Compare with something else?
Compare Radeon 780M with another →9 |
93 | Energy Efficiency | 86 |
26 | Quick Comparison Final Score | 20 |
| Phoenix | Graphics Processor | Krackan Point |
| 768 | Cores | 256 |
| 48 / 32 | TMUs / ROPs | 16 / 8 |
| 264.51 | Blender GPU | 122.02 |
| 24 | Forza Horizon 5 | 13 |
| 24 | The Witcher 3 | 12 |
| 29 | Counter-Strike 2 | 18 |
| 30 | Far Cry 6 | 16 |
| 14 | Hogwarts Legacy | - |
| 31 | Call of Duty | 19 |
| 14 | Ghost of Tsushima | 9 |
| 18 | Cyberpunk 2077 | 9 |
| 29 | Tomb Raider | 17 |
| 24 | Average FPS | 13 |
| 31 | 1080p High | 18 |
| 24 | 1080p Ultra | 13 |
| 16 | 1440p Ultra | 10 |
| 9 | 4K Ultra | - |
| Low | Margin of Error | High |
| 32713 | GB6 Compute Score | 14025 |
| 86.4 img/sec | Background Blur | 31.8 img/sec |
| 35.8 img/sec | Face Detection | 16.8 img/sec |
| 1.03 Gpixels/sec | Horizon Detection | 0.46 Gpixels/sec |
| 1.36 Gpixels/sec | Edge Detection | 0.58 Gpixels/sec |
| 1.41 Gpixels/sec | Gaussian Blur | 0.42 Gpixels/sec |
| 0.41 Gpixels/sec | Feature Matching | 0.18 Gpixels/sec |
| 132.4 Gpixels/sec | Stereo Matching | 52.5 Gpixels/sec |
| 4470.7 FPS | Particle Physics | 2048.6 FPS |
| OpenCL | API | OpenCL |
| 6851 | G3D Mark Score | — |
| 889 | G2D Mark | — |
| 66 FPS | DirectX 11 | — |
| 30 FPS | DirectX 12 | — |
| 3620 Ops/s | GPU Compute | — |
| 9091 | GB6 ML Single Precision | 4884 |
| 13510 | GB6 ML Half Precision | 6067 |
| 6786 | GB6 ML Quantized | 3946 |
| 3860 | Image Classification (SP) | 1988 |
| 5435 | Image Segmentation (HP) | 2184 |
| 10580 | Image Super Resolution (Q) | 4788 |
| 12855 | Face Detection (HP) | 6857 |
| 34716 | Pose Estimation (Q) | 17396 |
| 2578 | Text Classification (SP) | 1628 |
| 3897 | Machine Translation (HP) | 2053 |
| 3078 | Object Detection (SP) | 1825 |
| 14989 | Depth Estimation (Q) | 8471 |
| 78608 | Style Transfer (SP) | 31032 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 86-90 GPixel/s | Pixel Fill Rate | 23 GPixel/s |
| 130-134 GTexel/s | Texture Fill Rate | 46 GTexel/s |
| 4.1-4.3 TFLOPS | FLOPS (FP32) | 1.5 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| — | Memory Clock | — |
| — | Effective Memory Speed | — |
| — | Bus | — |
| — | ECC | — |
| — | Memory Bandwidth | — |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x16 |
| 15 W | TGP | 15-54 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 4 nm |
| 178 mm² | Die Size | — |
| 25.4 billion | Transistor Count | — |
| 142.7 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 2.1 |
| — | CUDA | No |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 2.1 | DisplayPort | 2.1 |
| Amd | Vendor | Amd |
| Integrated | Build | Integrated |
| January 4, 2023 | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Generic | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| RDNA 3.0 | Architecture | RDNA 3.5 |
| Phoenix | GPU Codename | Krackan Point |
| -AMD Ryzen 7 7840Uor above | Recommended CPU | -AMD Ryzen AI 5 340or above |
| 2662 | Steel Nomad Lite Score | 1293 |
| 2787 | Time Spy | 1700 |
| 11490 | Solar Bay | 7155 |
| 1579 | Port Royal | 577 |
| 7881 | Fire Strike | 5317 |
| 5315 | Wild Life Extreme | — |
| 33499 | Night Raid | 22727 |
| 800 MHz | Base Clock | 400 MHz |
| 2700-2800 MHz (configurable) | Boost Clock | 2900 MHz |
| 768 | Shading Units | 256 |
| 48 | Texture Mapping Units (TMUs) | 16 |
| 32 | Render Output Units (ROPs) | 8 |
| 12 | Compute Units (Pipelines) | 4 |
| — | Tensor Cores | No |
| 12 | Ray-tracing Cores | 4 |
| 128KB per cluster | L1 Cache | 512KB per cluster |
| 2MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |