Quick/Comparisons
38 | Gaming | 29 |
48 | Workstation | 34 |
46 | AI/ML |
Compare with something else?
Compare Apple M4 Max with another →26 |
87 | Energy Efficiency | 50 |
50 | Quick Comparison Final Score | 34 |
| Custom | Graphics Processor | Navi 22 |
| 5120 | Cores | 2304 |
| 320 / 160 | TMUs / ROPs | 144 / 64 |
| 5183.27 | Blender GPU | 1185.54 |
| — | Forza Horizon 5 | 74 |
| — | The Witcher 3 | 95 |
| — | Counter-Strike 2 | 131 |
| — | Far Cry 6 | 90 |
| — | Hogwarts Legacy | 56 |
| — | Call of Duty | 86 |
| — | Ghost of Tsushima | 57 |
| — | Cyberpunk 2077 | 63 |
| — | Tomb Raider | 105 |
| — | Average FPS | 84 |
| — | 1080p High | 106 |
| — | 1080p Ultra | 84 |
| — | 1440p Ultra | 58 |
| — | 4K Ultra | 32 |
| — | Margin of Error | High |
| 116754 | GB6 Compute Score | 92153 |
| 195 img/sec | Background Blur | 209.2 img/sec |
| 125.9 img/sec | Face Detection | 115.4 img/sec |
| 4.82 Gpixels/sec | Horizon Detection | 3.3 Gpixels/sec |
| 7.47 Gpixels/sec | Edge Detection | 4.7 Gpixels/sec |
| 5.8 Gpixels/sec | Gaussian Blur | 3.81 Gpixels/sec |
| 1.06 Gpixels/sec | Feature Matching | 0.94 Gpixels/sec |
| 417.4 Gpixels/sec | Stereo Matching | 327.1 Gpixels/sec |
| 17079.9 FPS | Particle Physics | 13207.5 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 13617 |
| — | G2D Mark | 554 |
| — | DirectX 11 | 129 FPS |
| — | DirectX 12 | 65 FPS |
| — | GPU Compute | 5188 Ops/s |
| 23632 | GB6 ML Single Precision | 14369 |
| 26019 | GB6 ML Half Precision | 15396 |
| 24606 | GB6 ML Quantized | 12333 |
| 10302 | Image Classification (SP) | 5874 |
| 23763 | Image Segmentation (HP) | 8129 |
| 29314 | Image Super Resolution (Q) | 18554 |
| 42016 | Face Detection (HP) | 18625 |
| 105972 | Pose Estimation (Q) | 84252 |
| 2963 | Text Classification (SP) | 1089 |
| 6594 | Machine Translation (HP) | 3605 |
| 8935 | Object Detection (SP) | 7294 |
| 43143 | Depth Estimation (Q) | 31037 |
| 221563 | Style Transfer (SP) | 154983 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 252 GPixel/s | Pixel Fill Rate | 110-147 GPixel/s |
| 505 GTexel/s | Texture Fill Rate | 248-331 GTexel/s |
| 16.2 TFLOPS | FLOPS (FP32) | 7.9-10.6 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 10 GB |
| 8533 MHz | Memory Clock | 1750 MHz |
| — | Effective Memory Speed | 14000 Mbps |
| 512-bit | Bus | 160-bit |
| No | ECC | No |
| 546 GB/s | Memory Bandwidth | 280 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 50 W | TGP | 80-135 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 7 nm |
| — | Die Size | 335 mm² |
| — | Transistor Count | 17.2 billion |
| — | Transistor Density | 51.34 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 1.4 |
| Apple | Vendor | Amd |
| Integrated | Build | Discrete |
| October 30, 2024 | Released | June 1, 2021 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | RDNA 2.0 |
| Custom | GPU Codename | Navi 22 |
| -Apple M4 Max (16-Core)or above | Recommended CPU | -AMD Ryzen 7 5800Hor above |
| 14528 | Steel Nomad Lite Score | 8784 |
| — | Time Spy | 9496 |
| 61324 | Solar Bay | 37680 |
| — | Port Royal | 4554 |
| — | Fire Strike | 27957 |
| 36631 | Wild Life Extreme | 17363 |
| — | Night Raid | 72638 |
| 500 MHz | Base Clock | 1489 MHz |
| 1578 MHz | Boost Clock | 1720-2300 MHz (configurable) |
| 5120 | Shading Units | 2304 |
| 320 | Texture Mapping Units (TMUs) | 144 |
| 160 | Render Output Units (ROPs) | 64 |
| 640 | Compute Units (Pipelines) | 36 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 36 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 3MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |