Quick/Comparisons
14 | Gaming | 72 |
23 | Workstation | 70 |
10 | AI/ML |
Compare with something else?
Compare Apple M3 GPU with another →68 |
95 | Energy Efficiency | 45 |
30 | Quick Comparison Final Score | 70 |
| — | Graphics Processor | Navi 31 |
| 1280 | Cores | 5376 |
| 80 / 40 | TMUs / ROPs | 336 / 192 |
| 155.27 | Blender GPU | 3548.59 |
| — | Forza Horizon 5 | 157 |
| — | The Witcher 3 | 228 |
| — | Counter-Strike 2 | 223 |
| — | Far Cry 6 | 173 |
| — | Hogwarts Legacy | 126 |
| — | Call of Duty | 222 |
| — | Ghost of Tsushima | 129 |
| — | Cyberpunk 2077 | 158 |
| — | Tomb Raider | 247 |
| — | Average FPS | 185 |
| — | 1080p High | 219 |
| — | 1080p Ultra | 185 |
| — | 1440p Ultra | 144 |
| — | 4K Ultra | 85 |
| — | Margin of Error | Low |
| 30027 | GB6 Compute Score | 203754 |
| 60.3 img/sec | Background Blur | 419.8 img/sec |
| 40.8 img/sec | Face Detection | 240.5 img/sec |
| 1.21 Gpixels/sec | Horizon Detection | 8.72 Gpixels/sec |
| 1.64 Gpixels/sec | Edge Detection | 12 Gpixels/sec |
| 1.2 Gpixels/sec | Gaussian Blur | 9.88 Gpixels/sec |
| 0.37 Gpixels/sec | Feature Matching | 1.71 Gpixels/sec |
| 102.6 Gpixels/sec | Stereo Matching | 701.7 Gpixels/sec |
| 3293.3 FPS | Particle Physics | 26631.4 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 29015 |
| — | G2D Mark | 1241 |
| — | DirectX 11 | 340 FPS |
| — | DirectX 12 | 111 FPS |
| — | GPU Compute | 16851 Ops/s |
| 4120 | GB6 ML Single Precision | 39099 |
| 6992 | GB6 ML Half Precision | 47298 |
| 5638 | GB6 ML Quantized | 30875 |
| 1579 | Image Classification (SP) | 16951 |
| 2944 | Image Segmentation (HP) | 23234 |
| 4425 | Image Super Resolution (Q) | 41128 |
| 6661 | Face Detection (HP) | 67615 |
| 15020 | Pose Estimation (Q) | 237026 |
| 2984 | Text Classification (SP) | 4961 |
| 5876 | Machine Translation (HP) | 7043 |
| 1826 | Object Detection (SP) | 18737 |
| 9339 | Depth Estimation (Q) | 67746 |
| 22291 | Style Transfer (SP) | 457919 |
| Core ML | Framework | ONNX |
| CPU | Backend | DirectML |
| 55 GPixel/s | Pixel Fill Rate | 460 GPixel/s |
| 110 GTexel/s | Texture Fill Rate | 804 GTexel/s |
| 3.5 TFLOPS | FLOPS (FP32) | 51.5 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 20 GB |
| 6400 MHz | Memory Clock | 2500 MHz |
| 12800 Mbps | Effective Memory Speed | 20000 Mbps |
| 128-bit | Bus | 320-bit |
| No | ECC | No |
| 102.4 GB/s | Memory Bandwidth | 800 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 15 W | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | 529 mm² |
| 13.8 billion | Transistor Count | 57 billion |
| — | Transistor Density | 107.75 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.2 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1 |
| Apple | Vendor | Amd |
| Integrated | Build | Discrete |
| October 31, 2023 | Released | December 13, 2023 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | RDNA 3.0 |
| — | GPU Codename | Navi 31 |
| -Apple M3or above | Recommended CPU | -Intel Core i7 13700Kor above |
| 3478 | Steel Nomad Lite Score | 24675 |
| — | Time Spy | 27067 |
| 13529 | Solar Bay | 104912 |
| — | Port Royal | 14358 |
| — | Fire Strike | 67256 |
| 8229 | Wild Life Extreme | 48319 |
| — | Night Raid | 176267 |
| 500 MHz | Base Clock | 1387 MHz |
| 1380 MHz | Boost Clock | 2394 MHz |
| 1280 | Shading Units | 5376 |
| 80 | Texture Mapping Units (TMUs) | 336 |
| 40 | Render Output Units (ROPs) | 192 |
| 160 | Compute Units (Pipelines) | — |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 84 |
| — | L1 Cache | 256KB per cluster |
| — | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |