Quick/Comparisons
26 | Gaming | 17 |
39 | Workstation | 29 |
29 | AI/ML |
Compare with something else?
Compare Apple M2 Max with another →18 |
76 | Energy Efficiency | 59 |
38 | Quick Comparison Final Score | 27 |
| — | Graphics Processor | GA106 |
| 4864 | Cores | 2560 |
| 304 / 152 | TMUs / ROPs | 80 / 48 |
| 1777.05 | Blender GPU | 1262.73 |
| — | Forza Horizon 5 | 44 |
| — | The Witcher 3 | 47 |
| — | Counter-Strike 2 | 74 |
| — | Far Cry 6 | 50 |
| — | Hogwarts Legacy | 26 |
| — | Call of Duty | 36 |
| — | Ghost of Tsushima | 23 |
| — | Cyberpunk 2077 | 33 |
| — | Tomb Raider | 56 |
| — | Average FPS | 43 |
| — | 1080p High | 55 |
| — | 1080p Ultra | 43 |
| — | 1440p Ultra | 30 |
| — | 4K Ultra | 14 |
| — | Margin of Error | Low |
| 86936 | GB6 Compute Score | 57201 |
| 149 img/sec | Background Blur | 92.8 img/sec |
| 98.1 img/sec | Face Detection | 54.2 img/sec |
| 3.8 Gpixels/sec | Horizon Detection | 2.47 Gpixels/sec |
| 6.88 Gpixels/sec | Edge Detection | 3.32 Gpixels/sec |
| 4.44 Gpixels/sec | Gaussian Blur | 2.63 Gpixels/sec |
| 0.73 Gpixels/sec | Feature Matching | 0.7 Gpixels/sec |
| 264.9 Gpixels/sec | Stereo Matching | 236.9 Gpixels/sec |
| 11144.2 FPS | Particle Physics | 7148.8 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 9487 |
| — | G2D Mark | 505 |
| — | DirectX 11 | 65 FPS |
| — | DirectX 12 | 47 FPS |
| — | GPU Compute | 4252 Ops/s |
| 15005 | GB6 ML Single Precision | 9891 |
| 16456 | GB6 ML Half Precision | 18270 |
| 15418 | GB6 ML Quantized | 6987 |
| 6657 | Image Classification (SP) | 4240 |
| 13854 | Image Segmentation (HP) | 9190 |
| 18642 | Image Super Resolution (Q) | 9374 |
| 27965 | Face Detection (HP) | 18335 |
| 83144 | Pose Estimation (Q) | 36989 |
| 2377 | Text Classification (SP) | 2035 |
| 2052 | Machine Translation (HP) | 2687 |
| 6495 | Object Detection (SP) | 5174 |
| 31105 | Depth Estimation (Q) | 16537 |
| 135686 | Style Transfer (SP) | 77854 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 212 GPixel/s | Pixel Fill Rate | 50-81 GPixel/s |
| 425 GTexel/s | Texture Fill Rate | 83-136 GTexel/s |
| 13.6 TFLOPS | FLOPS (FP32) | 5.3-8.7 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 4 GB |
| 6400 MHz | Memory Clock | 1500 MHz |
| 12800 Mbps | Effective Memory Speed | 12000 Mbps |
| 512-bit | Bus | 128-bit |
| No | ECC | No |
| 409.6 GB/s | Memory Bandwidth | 192 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 70 W | TGP | 60-95 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 5 nm | Fabrication Process | 8 nm |
| — | Die Size | 276 mm² |
| 52 billion | Transistor Count | 12 billion |
| — | Transistor Density | 43.48 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.6 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| January 17, 2023 | Released | April 12, 2021 |
| Laptop | Case | Laptop |
| Professional | Purpose | Professional |
| High-end | Segment | Mid-range |
| Apple M GPU | Architecture | Ampere |
| — | GPU Codename | GA106 |
| — | Recommended CPU | -Intel Core i7 12800Hor above |
| 9413 | Steel Nomad Lite Score | 4397 |
| — | Time Spy | 4723 |
| 30427 | Solar Bay | 19912 |
| — | Port Royal | 2895 |
| — | Fire Strike | 11357 |
| 24969 | Wild Life Extreme | 8429 |
| — | Night Raid | 49889 |
| 450 MHz | Base Clock | 735-1463 MHz (configurable) |
| 1398 MHz | Boost Clock | 1035-1695 MHz (configurable) |
| 4864 | Shading Units | 2560 |
| 304 | Texture Mapping Units (TMUs) | 80 |
| 152 | Render Output Units (ROPs) | 48 |
| 608 | Compute Units (Pipelines) | 20 |
| — | Tensor Cores | 80 |
| — | Ray-tracing Cores | 20 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |