Quick/Comparisons
26 | Gaming | 28 |
39 | Workstation | 37 |
29 | AI/ML |
Compare with something else?
Compare Apple M2 Max with another →28 |
76 | Energy Efficiency | 56 |
38 | Quick Comparison Final Score | 35 |
| — | Graphics Processor | AD107 |
| 4864 | Cores | 3072 |
| 304 / 152 | TMUs / ROPs | 96 / 48 |
| 1777.05 | Blender GPU | 2498.74 |
| — | Forza Horizon 5 | 62 |
| — | The Witcher 3 | 90 |
| — | Counter-Strike 2 | 119 |
| — | Far Cry 6 | 75 |
| — | Hogwarts Legacy | 50 |
| — | Call of Duty | 62 |
| — | Ghost of Tsushima | 42 |
| — | Cyberpunk 2077 | 52 |
| — | Tomb Raider | 88 |
| — | Average FPS | 71 |
| — | 1080p High | 89 |
| — | 1080p Ultra | 71 |
| — | 1440p Ultra | 52 |
| — | 4K Ultra | 28 |
| — | Margin of Error | High |
| 86936 | GB6 Compute Score | 81913 |
| 149 img/sec | Background Blur | 149.7 img/sec |
| 98.1 img/sec | Face Detection | 88.5 img/sec |
| 3.8 Gpixels/sec | Horizon Detection | 3.24 Gpixels/sec |
| 6.88 Gpixels/sec | Edge Detection | 4.3 Gpixels/sec |
| 4.44 Gpixels/sec | Gaussian Blur | 4.3 Gpixels/sec |
| 0.73 Gpixels/sec | Feature Matching | 1.06 Gpixels/sec |
| 264.9 Gpixels/sec | Stereo Matching | 278.2 Gpixels/sec |
| 11144.2 FPS | Particle Physics | 9706.8 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 14863 |
| — | G2D Mark | 597 |
| — | DirectX 11 | 124 FPS |
| — | DirectX 12 | 66 FPS |
| — | GPU Compute | 5612 Ops/s |
| 15005 | GB6 ML Single Precision | 15637 |
| 16456 | GB6 ML Half Precision | 25753 |
| 15418 | GB6 ML Quantized | 12373 |
| 6657 | Image Classification (SP) | 6324 |
| 13854 | Image Segmentation (HP) | 13952 |
| 18642 | Image Super Resolution (Q) | 19043 |
| 27965 | Face Detection (HP) | 28439 |
| 83144 | Pose Estimation (Q) | 69947 |
| 2377 | Text Classification (SP) | 2887 |
| 2052 | Machine Translation (HP) | 3267 |
| 6495 | Object Detection (SP) | 7742 |
| 31105 | Depth Estimation (Q) | 29911 |
| 135686 | Style Transfer (SP) | 131880 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 212 GPixel/s | Pixel Fill Rate | 60-113 GPixel/s |
| 425 GTexel/s | Texture Fill Rate | 120-227 GTexel/s |
| 13.6 TFLOPS | FLOPS (FP32) | 7.6-14.5 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| 6400 MHz | Memory Clock | 2000 MHz |
| 12800 Mbps | Effective Memory Speed | 16000 Mbps |
| 512-bit | Bus | 128-bit |
| No | ECC | No |
| 409.6 GB/s | Memory Bandwidth | 256 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 70 W | TGP | 35-140 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| — | Die Size | 159 mm² |
| 52 billion | Transistor Count | 18.9 billion |
| — | Transistor Density | 118.87 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.9 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 3 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| January 17, 2023 | Released | March 21, 2023 |
| Laptop | Case | Laptop |
| Professional | Purpose | Professional |
| High-end | Segment | Mid-range |
| Apple M GPU | Architecture | Ada Lovelace |
| — | GPU Codename | AD107 |
| — | Recommended CPU | -Intel Core Ultra 7 165Hor above |
| 9413 | Steel Nomad Lite Score | 7995 |
| — | Time Spy | 7374 |
| 30427 | Solar Bay | 29213 |
| — | Port Royal | 4564 |
| — | Fire Strike | 19215 |
| 24969 | Wild Life Extreme | 14651 |
| — | Night Raid | 76011 |
| 450 MHz | Base Clock | — |
| 1398 MHz | Boost Clock | 1245-2360 MHz (configurable) |
| 4864 | Shading Units | 3072 |
| 304 | Texture Mapping Units (TMUs) | 96 |
| 152 | Render Output Units (ROPs) | 48 |
| 608 | Compute Units (Pipelines) | 24 |
| — | Tensor Cores | 96 |
| — | Ray-tracing Cores | 24 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 32MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |