Quick/Comparisons
21 | Gaming | 18 |
32 | Workstation | 25 |
33 | AI/ML |
Compare with something else?
Compare Apple M4 Pro with another →18 |
94 | Energy Efficiency | 59 |
37 | Quick Comparison Final Score | 27 |
| Custom | Graphics Processor | GA107 |
| 2048 | Cores | 2048 |
| 128 / 64 | TMUs / ROPs | 64 / 40 |
| 2355.52 | Blender GPU | 1162.84 |
| — | Forza Horizon 5 | 44 |
| — | The Witcher 3 | 55 |
| — | Counter-Strike 2 | 80 |
| — | Far Cry 6 | 53 |
| — | Hogwarts Legacy | 27 |
| — | Call of Duty | 39 |
| — | Ghost of Tsushima | 24 |
| — | Cyberpunk 2077 | 34 |
| — | Tomb Raider | 59 |
| — | Average FPS | 46 |
| — | 1080p High | 60 |
| — | 1080p Ultra | 46 |
| — | 1440p Ultra | 32 |
| — | 4K Ultra | 17 |
| — | Margin of Error | Low |
| 61008 | GB6 Compute Score | 58733 |
| 106 img/sec | Background Blur | 88.6 img/sec |
| 73.1 img/sec | Face Detection | 57.3 img/sec |
| 2.59 Gpixels/sec | Horizon Detection | 2.53 Gpixels/sec |
| 3.8 Gpixels/sec | Edge Detection | 3.33 Gpixels/sec |
| 2.4 Gpixels/sec | Gaussian Blur | 2.55 Gpixels/sec |
| 0.73 Gpixels/sec | Feature Matching | 0.76 Gpixels/sec |
| 198.6 Gpixels/sec | Stereo Matching | 256.5 Gpixels/sec |
| 8166.3 FPS | Particle Physics | 7465.5 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 9493 |
| — | G2D Mark | 490 |
| — | DirectX 11 | 71 FPS |
| — | DirectX 12 | 46 FPS |
| — | GPU Compute | 3860 Ops/s |
| 16605 | GB6 ML Single Precision | 10038 |
| 18809 | GB6 ML Half Precision | 19152 |
| 17506 | GB6 ML Quantized | 6984 |
| 7548 | Image Classification (SP) | 4349 |
| 15108 | Image Segmentation (HP) | 11416 |
| 20789 | Image Super Resolution (Q) | 8973 |
| 28665 | Face Detection (HP) | 18927 |
| 57124 | Pose Estimation (Q) | 34631 |
| 2888 | Text Classification (SP) | 2269 |
| 6086 | Machine Translation (HP) | 3539 |
| 6804 | Object Detection (SP) | 5046 |
| 32732 | Depth Estimation (Q) | 15772 |
| 123465 | Style Transfer (SP) | 75260 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 101 GPixel/s | Pixel Fill Rate | 42-70 GPixel/s |
| 202 GTexel/s | Texture Fill Rate | 68-111 GTexel/s |
| 6.5 TFLOPS | FLOPS (FP32) | 4.3-7.1 TFLOPS |
| — | Memory Size | 4 GB |
| 8533 MHz | Memory Clock | 1500 MHz |
| 15000 Mbps | Effective Memory Speed | 12000 Mbps |
| 192-bit | Bus | 128-bit |
| No | ECC | No |
| 273 GB/s | Memory Bandwidth | 192 GB/s |
| System Shared | Memory Type | GDDR6 |
| Custom | Interface | PCIe 4.0 x16 |
| 26 W | TGP | 35-95 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 3 nm | Fabrication Process | 8 nm |
| — | Die Size | 200 mm² |
| — | Transistor Count | 8.7 billion |
| — | Transistor Density | 43.5 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 29, 2024 | Released | January 1, 2021 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Ampere |
| Custom | GPU Codename | GA107 |
| -Apple M4 Pro (12-Core)or above | Recommended CPU | — |
| 6944 | Steel Nomad Lite Score | 4914 |
| — | Time Spy | 4884 |
| 28721 | Solar Bay | 21603 |
| — | Port Royal | 552 |
| — | Fire Strike | 12561 |
| 16466 | Wild Life Extreme | 9421 |
| — | Night Raid | 53654 |
| 500 MHz | Base Clock | 712-1530 MHz (configurable) |
| 1578 MHz | Boost Clock | 1057-1740 MHz (configurable) |
| 2048 | Shading Units | 2048 |
| 128 | Texture Mapping Units (TMUs) | 64 |
| 64 | Render Output Units (ROPs) | 40 |
| 256 | Compute Units (Pipelines) | 16 |
| — | Tensor Cores | 64 |
| — | Ray-tracing Cores | 16 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |