Quick/Comparisons
21 | Gaming | 31 |
32 | Workstation | 38 |
33 | AI/ML |
Compare with something else?
Compare Apple M4 Pro with another →27 |
94 | Energy Efficiency | 43 |
37 | Quick Comparison Final Score | 33 |
| Custom | Graphics Processor | DG2-512 |
| 2048 | Cores | 3584 |
| 128 / 64 | TMUs / ROPs | 224 / 112 |
| 2355.52 | Blender GPU | 2033.41 |
| — | Forza Horizon 5 | 68 |
| — | The Witcher 3 | 114 |
| — | Counter-Strike 2 | 108 |
| — | Far Cry 6 | 87 |
| — | Hogwarts Legacy | 50 |
| — | Call of Duty | 69 |
| — | Ghost of Tsushima | 51 |
| — | Cyberpunk 2077 | 69 |
| — | Tomb Raider | 98 |
| — | Average FPS | 79 |
| — | 1080p High | 98 |
| — | 1080p Ultra | 79 |
| — | 1440p Ultra | 59 |
| — | 4K Ultra | 33 |
| — | Margin of Error | Low |
| 61008 | GB6 Compute Score | 99280 |
| 106 img/sec | Background Blur | 145.2 img/sec |
| 73.1 img/sec | Face Detection | 82 img/sec |
| 2.59 Gpixels/sec | Horizon Detection | 3.35 Gpixels/sec |
| 3.8 Gpixels/sec | Edge Detection | 5.01 Gpixels/sec |
| 2.4 Gpixels/sec | Gaussian Blur | 7.59 Gpixels/sec |
| 0.73 Gpixels/sec | Feature Matching | 0.81 Gpixels/sec |
| 198.6 Gpixels/sec | Stereo Matching | 462.4 Gpixels/sec |
| 8166.3 FPS | Particle Physics | 18623.1 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 12620 |
| — | G2D Mark | 737 |
| — | DirectX 11 | 73 FPS |
| — | DirectX 12 | 70 FPS |
| — | GPU Compute | 5307 Ops/s |
| 16605 | GB6 ML Single Precision | 12178 |
| 18809 | GB6 ML Half Precision | 12796 |
| 17506 | GB6 ML Quantized | 9086 |
| 7548 | Image Classification (SP) | 5475 |
| 15108 | Image Segmentation (HP) | 13781 |
| 20789 | Image Super Resolution (Q) | 11612 |
| 28665 | Face Detection (HP) | 18556 |
| 57124 | Pose Estimation (Q) | 58801 |
| 2888 | Text Classification (SP) | 824 |
| 6086 | Machine Translation (HP) | 2397 |
| 6804 | Object Detection (SP) | 6895 |
| 32732 | Depth Estimation (Q) | 22219 |
| 123465 | Style Transfer (SP) | 161148 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 101 GPixel/s | Pixel Fill Rate | 269 GPixel/s |
| 202 GTexel/s | Texture Fill Rate | 538 GTexel/s |
| 6.5 TFLOPS | FLOPS (FP32) | 17.2 TFLOPS |
| — | Memory Size | 8 GB |
| 8533 MHz | Memory Clock | 2000 MHz |
| 15000 Mbps | Effective Memory Speed | 16000 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | No |
| 273 GB/s | Memory Bandwidth | 512 GB/s |
| System Shared | Memory Type | GDDR6 |
| Custom | Interface | PCIe 4.0 x16 |
| 26 W | TGP | 225 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 6 nm |
| — | Die Size | 406 mm² |
| — | Transistor Count | 21 billion |
| — | Transistor Density | 51.72 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2 |
| Apple | Vendor | Intel |
| Integrated | Build | Discrete |
| October 29, 2024 | Released | October 12, 2023 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Generation 12.7 |
| Custom | GPU Codename | DG2-512 |
| -Apple M4 Pro (12-Core)or above | Recommended CPU | -Intel Core i5 12500or above |
| 6944 | Steel Nomad Lite Score | 10846 |
| — | Time Spy | 12425 |
| 28721 | Solar Bay | 45771 |
| — | Port Royal | 6594 |
| — | Fire Strike | 30444 |
| 16466 | Wild Life Extreme | 23682 |
| — | Night Raid | 110785 |
| 500 MHz | Base Clock | 2050 MHz |
| 1578 MHz | Boost Clock | 2400 MHz |
| 2048 | Shading Units | 3584 |
| 128 | Texture Mapping Units (TMUs) | 224 |
| 64 | Render Output Units (ROPs) | 112 |
| 256 | Compute Units (Pipelines) | — |
| — | Tensor Cores | 448 |
| — | Ray-tracing Cores | 28 |
| — | L1 Cache | — |
| — | L2 Cache | 16MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |