Quick/Comparisons
38 | Gaming | 5 |
48 | Workstation | 11 |
46 | AI/ML |
Compare with something else?
Compare Apple M4 Max with another →4 |
87 | Energy Efficiency | 89 |
50 | Quick Comparison Final Score | 20 |
| Custom | Graphics Processor | Mendocino |
| 5120 | Cores | 128 |
| 320 / 160 | TMUs / ROPs | 8 / 4 |
| 5183.27 | Blender GPU | 47.24 |
| — | Forza Horizon 5 | — |
| — | The Witcher 3 | — |
| — | Counter-Strike 2 | — |
| — | Far Cry 6 | — |
| — | Hogwarts Legacy | — |
| — | Call of Duty | — |
| — | Ghost of Tsushima | — |
| — | Cyberpunk 2077 | — |
| — | Tomb Raider | — |
| — | Average FPS | — |
| — | 1080p High | — |
| — | 1080p Ultra | — |
| — | 1440p Ultra | — |
| — | 4K Ultra | — |
| — | Margin of Error | — |
| 116754 | GB6 Compute Score | 5099 |
| 195 img/sec | Background Blur | 12 img/sec |
| 125.9 img/sec | Face Detection | 6.42 img/sec |
| 4.82 Gpixels/sec | Horizon Detection | 0.16 Gpixels/sec |
| 7.47 Gpixels/sec | Edge Detection | 0.23 Gpixels/sec |
| 5.8 Gpixels/sec | Gaussian Blur | 0.16 Gpixels/sec |
| 1.06 Gpixels/sec | Feature Matching | 0.07 Gpixels/sec |
| 417.4 Gpixels/sec | Stereo Matching | 18.2 Gpixels/sec |
| 17079.9 FPS | Particle Physics | 828.6 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 1810 |
| — | G2D Mark | 536 |
| — | DirectX 11 | 17 FPS |
| — | DirectX 12 | 7 FPS |
| — | GPU Compute | 771 Ops/s |
| 23632 | GB6 ML Single Precision | 1917 |
| 26019 | GB6 ML Half Precision | 2053 |
| 24606 | GB6 ML Quantized | 1571 |
| 10302 | Image Classification (SP) | 660 |
| 23763 | Image Segmentation (HP) | 627 |
| 29314 | Image Super Resolution (Q) | 2053 |
| 42016 | Face Detection (HP) | 2153 |
| 105972 | Pose Estimation (Q) | 5787 |
| 2963 | Text Classification (SP) | 713 |
| 6594 | Machine Translation (HP) | 1114 |
| 8935 | Object Detection (SP) | 709 |
| 43143 | Depth Estimation (Q) | 3233 |
| 221563 | Style Transfer (SP) | 11091 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 252 GPixel/s | Pixel Fill Rate | 8-9 GPixel/s |
| 505 GTexel/s | Texture Fill Rate | 15-18 GTexel/s |
| 16.2 TFLOPS | FLOPS (FP32) | 0.5-0.6 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| 8533 MHz | Memory Clock | — |
| — | Effective Memory Speed | — |
| 512-bit | Bus | — |
| No | ECC | No |
| 546 GB/s | Memory Bandwidth | — |
| Custom | Interface | PCIe 4.0 x8 |
| 50 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 6 nm |
| — | Die Size | 122 mm² |
| — | Transistor Count | 3.4 billion |
| — | Transistor Density | 27.87 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | — |
| Apple | Vendor | Amd |
| Integrated | Build | Integrated |
| October 30, 2024 | Released | October 1, 2022 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Apple M GPU | Architecture | RDNA 2.0 |
| Custom | GPU Codename | Mendocino |
| -Apple M4 Max (16-Core)or above | Recommended CPU | -AMD Ryzen 5 7520Uor above |
| 14528 | Steel Nomad Lite Score | 447 |
| — | Time Spy | 519 |
| 61324 | Solar Bay | 2078 |
| — | Port Royal | 309 |
| — | Fire Strike | 1760 |
| 36631 | Wild Life Extreme | 994 |
| — | Night Raid | 7447 |
| 500 MHz | Base Clock | 400 MHz |
| 1578 MHz | Boost Clock | 1900-2200 MHz (configurable) |
| 5120 | Shading Units | 128 |
| 320 | Texture Mapping Units (TMUs) | 8 |
| 160 | Render Output Units (ROPs) | 4 |
| 640 | Compute Units (Pipelines) | 2 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 2 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |