Quick/Comparisons
33 | Gaming | 6 |
42 | Workstation | 14 |
39 | AI/ML |
Compare with something else?
Compare Apple M3 Max with another →7 |
82 | Energy Efficiency | 71 |
44 | Quick Comparison Final Score | 19 |
| — | Graphics Processor | TU117 |
| 5120 | Cores | 896 |
| 320 / 160 | TMUs / ROPs | 56 / 32 |
| 3797.82 | Blender GPU | 201.01 |
| — | Forza Horizon 5 | 10 |
| — | The Witcher 3 | 12 |
| — | Counter-Strike 2 | 22 |
| — | Far Cry 6 | 21 |
| — | Hogwarts Legacy | 10 |
| — | Call of Duty | 23 |
| — | Ghost of Tsushima | - |
| — | Cyberpunk 2077 | - |
| — | Tomb Raider | 17 |
| — | Average FPS | 14 |
| — | 1080p High | 20 |
| — | 1080p Ultra | 14 |
| — | 1440p Ultra | 10 |
| — | 4K Ultra | - |
| — | Margin of Error | Medium |
| 94528 | GB6 Compute Score | 34221 |
| 157.6 img/sec | Background Blur | 65.7 img/sec |
| 100.9 img/sec | Face Detection | 33.3 img/sec |
| 3.99 Gpixels/sec | Horizon Detection | 1.01 Gpixels/sec |
| 6.04 Gpixels/sec | Edge Detection | 1.39 Gpixels/sec |
| 5 Gpixels/sec | Gaussian Blur | 1.61 Gpixels/sec |
| 0.84 Gpixels/sec | Feature Matching | 0.48 Gpixels/sec |
| 363.8 Gpixels/sec | Stereo Matching | 176 Gpixels/sec |
| 12226.9 FPS | Particle Physics | 5012.4 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 3718 |
| — | G2D Mark | 305 |
| — | DirectX 11 | 26 FPS |
| — | DirectX 12 | 23 FPS |
| — | GPU Compute | 1867 Ops/s |
| 20068 | GB6 ML Single Precision | 4394 |
| 22390 | GB6 ML Half Precision | 4387 |
| 20681 | GB6 ML Quantized | 3246 |
| 8685 | Image Classification (SP) | 1911 |
| 20739 | Image Segmentation (HP) | 2536 |
| 22775 | Image Super Resolution (Q) | 4111 |
| 37676 | Face Detection (HP) | 5175 |
| 91609 | Pose Estimation (Q) | 13374 |
| 2909 | Text Classification (SP) | 1514 |
| 5274 | Machine Translation (HP) | 1481 |
| 7480 | Object Detection (SP) | 2070 |
| 38212 | Depth Estimation (Q) | 7813 |
| 190681 | Style Transfer (SP) | 36156 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 221 GPixel/s | Pixel Fill Rate | 30-50 GPixel/s |
| 442 GTexel/s | Texture Fill Rate | 52-88 GTexel/s |
| 14.1 TFLOPS | FLOPS (FP32) | 1.7-2.8 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 2 GB |
| 6400 MHz | Memory Clock | 1250 MHz |
| 12800 Mbps | Effective Memory Speed | 10000 Mbps |
| 512-bit | Bus | 64-bit |
| No | ECC | — |
| 409.6 GB/s | Memory Bandwidth | 80 GB/s |
| Custom | Interface | PCIe 4.0 x4 |
| 60 W | TGP | 10-30 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 12 nm |
| — | Die Size | 200 mm² |
| 56 billion | Transistor Count | 4.7 billion |
| — | Transistor Density | 23.5 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 1.2 |
| — | CUDA | 7.5 |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | 1.4 |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 31, 2023 | Released | August 25, 2020 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Apple M GPU | Architecture | Turing |
| — | GPU Codename | TU117 |
| -Apple M3 Maxor above | Recommended CPU | -Intel Core i5 11300Hor above |
| 12391 | Steel Nomad Lite Score | 1174 |
| — | Time Spy | 2118 |
| 49656 | Solar Bay | — |
| — | Port Royal | — |
| — | Fire Strike | 5267 |
| 30787 | Wild Life Extreme | 4259 |
| — | Night Raid | 26243 |
| 500 MHz | Base Clock | 720-1395 MHz (configurable) |
| 1380 MHz | Boost Clock | 930-1575 MHz (configurable) |
| 5120 | Shading Units | 896 |
| 320 | Texture Mapping Units (TMUs) | 56 |
| 160 | Render Output Units (ROPs) | 32 |
| 640 | Compute Units (Pipelines) | 14 |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | No |
| — | L1 Cache | 64KB per cluster |
| — | L2 Cache | 512KB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |