Quick/Comparisons
38 | Gaming | 10 |
48 | Workstation | 15 |
46 | AI/ML |
Compare with something else?
Compare Apple M4 Max with another →17 |
87 | Energy Efficiency | 93 |
50 | Quick Comparison Final Score | 26 |
| Custom | Graphics Processor | Phoenix |
| 5120 | Cores | 768 |
| 320 / 160 | TMUs / ROPs | 48 / 32 |
| 5183.27 | Blender GPU | 264.51 |
| — | Forza Horizon 5 | 24 |
| — | The Witcher 3 | 24 |
| — | Counter-Strike 2 | 29 |
| — | Far Cry 6 | 30 |
| — | Hogwarts Legacy | 14 |
| — | Call of Duty | 31 |
| — | Ghost of Tsushima | 14 |
| — | Cyberpunk 2077 | 18 |
| — | Tomb Raider | 29 |
| — | Average FPS | 24 |
| — | 1080p High | 31 |
| — | 1080p Ultra | 24 |
| — | 1440p Ultra | 16 |
| — | 4K Ultra | 9 |
| — | Margin of Error | Low |
| 116754 | GB6 Compute Score | 32713 |
| 195 img/sec | Background Blur | 86.4 img/sec |
| 125.9 img/sec | Face Detection | 35.8 img/sec |
| 4.82 Gpixels/sec | Horizon Detection | 1.03 Gpixels/sec |
| 7.47 Gpixels/sec | Edge Detection | 1.36 Gpixels/sec |
| 5.8 Gpixels/sec | Gaussian Blur | 1.41 Gpixels/sec |
| 1.06 Gpixels/sec | Feature Matching | 0.41 Gpixels/sec |
| 417.4 Gpixels/sec | Stereo Matching | 132.4 Gpixels/sec |
| 17079.9 FPS | Particle Physics | 4470.7 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 6851 |
| — | G2D Mark | 889 |
| — | DirectX 11 | 66 FPS |
| — | DirectX 12 | 30 FPS |
| — | GPU Compute | 3620 Ops/s |
| 23632 | GB6 ML Single Precision | 9091 |
| 26019 | GB6 ML Half Precision | 13510 |
| 24606 | GB6 ML Quantized | 6786 |
| 10302 | Image Classification (SP) | 3860 |
| 23763 | Image Segmentation (HP) | 5435 |
| 29314 | Image Super Resolution (Q) | 10580 |
| 42016 | Face Detection (HP) | 12855 |
| 105972 | Pose Estimation (Q) | 34716 |
| 2963 | Text Classification (SP) | 2578 |
| 6594 | Machine Translation (HP) | 3897 |
| 8935 | Object Detection (SP) | 3078 |
| 43143 | Depth Estimation (Q) | 14989 |
| 221563 | Style Transfer (SP) | 78608 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 252 GPixel/s | Pixel Fill Rate | 86-90 GPixel/s |
| 505 GTexel/s | Texture Fill Rate | 130-134 GTexel/s |
| 16.2 TFLOPS | FLOPS (FP32) | 4.1-4.3 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| 8533 MHz | Memory Clock | — |
| — | Effective Memory Speed | — |
| 512-bit | Bus | — |
| No | ECC | — |
| 546 GB/s | Memory Bandwidth | — |
| Custom | Interface | PCIe 4.0 x8 |
| 50 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 4 nm |
| — | Die Size | 178 mm² |
| — | Transistor Count | 25.4 billion |
| — | Transistor Density | 142.7 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1 |
| Apple | Vendor | Amd |
| Integrated | Build | Integrated |
| October 30, 2024 | Released | January 4, 2023 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | RDNA 3.0 |
| Custom | GPU Codename | Phoenix |
| -Apple M4 Max (16-Core)or above | Recommended CPU | -AMD Ryzen 7 7840Uor above |
| 14528 | Steel Nomad Lite Score | 2662 |
| — | Time Spy | 2787 |
| 61324 | Solar Bay | 11490 |
| — | Port Royal | 1579 |
| — | Fire Strike | 7881 |
| 36631 | Wild Life Extreme | 5315 |
| — | Night Raid | 33499 |
| 500 MHz | Base Clock | 800 MHz |
| 1578 MHz | Boost Clock | 2700-2800 MHz (configurable) |
| 5120 | Shading Units | 768 |
| 320 | Texture Mapping Units (TMUs) | 48 |
| 160 | Render Output Units (ROPs) | 32 |
| 640 | Compute Units (Pipelines) | 12 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 12 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |