Quick/Comparisons
24 | Gaming | 31 |
34 | Workstation | 52 |
34 | AI/ML |
Compare with something else?
Compare Apple M4 Pro with another →31 |
94 | Energy Efficiency | 48 |
39 | Quick Comparison Final Score | 40 |
| Custom | Graphics Processor | GA104 |
| 2560 | Cores | 5888 |
| 160 / 80 | TMUs / ROPs | 184 / 96 |
| 2520.96 | Blender GPU | 2757.5 |
| — | Forza Horizon 5 | 71 |
| — | The Witcher 3 | 100 |
| — | Counter-Strike 2 | 137 |
| — | Far Cry 6 | 86 |
| — | Hogwarts Legacy | 56 |
| — | Call of Duty | 75 |
| — | Ghost of Tsushima | 52 |
| — | Cyberpunk 2077 | 66 |
| — | Tomb Raider | 100 |
| — | Average FPS | 83 |
| — | 1080p High | 104 |
| — | 1080p Ultra | 83 |
| — | 1440p Ultra | 60 |
| — | 4K Ultra | 34 |
| — | Margin of Error | High |
| 70029 | GB6 Compute Score | 119474 |
| 125.1 img/sec | Background Blur | 158.7 img/sec |
| 80 img/sec | Face Detection | 115.8 img/sec |
| 2.88 Gpixels/sec | Horizon Detection | 5.95 Gpixels/sec |
| 4.22 Gpixels/sec | Edge Detection | 8.2 Gpixels/sec |
| 2.98 Gpixels/sec | Gaussian Blur | 5.85 Gpixels/sec |
| 0.8 Gpixels/sec | Feature Matching | 1.13 Gpixels/sec |
| 235 Gpixels/sec | Stereo Matching | 505.2 Gpixels/sec |
| 9516.1 FPS | Particle Physics | 15517.5 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 16804 |
| — | G2D Mark | 714 |
| — | DirectX 11 | 131 FPS |
| — | DirectX 12 | 77 FPS |
| — | GPU Compute | 6679 Ops/s |
| 17327 | GB6 ML Single Precision | 14763 |
| 18455 | GB6 ML Half Precision | 23628 |
| 17831 | GB6 ML Quantized | 10163 |
| 8046 | Image Classification (SP) | 6159 |
| 15443 | Image Segmentation (HP) | 12031 |
| 20807 | Image Super Resolution (Q) | 15490 |
| 30860 | Face Detection (HP) | 29614 |
| 56783 | Pose Estimation (Q) | 65582 |
| 2888 | Text Classification (SP) | 1918 |
| 6167 | Machine Translation (HP) | 3097 |
| 7592 | Object Detection (SP) | 8192 |
| 33607 | Depth Estimation (Q) | 23635 |
| 126726 | Style Transfer (SP) | 142647 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 126 GPixel/s | Pixel Fill Rate | 99-143 GPixel/s |
| 252 GTexel/s | Texture Fill Rate | 190-273 GTexel/s |
| 8.1 TFLOPS | FLOPS (FP32) | 12.2-17.5 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 16 GB |
| 8533 MHz | Memory Clock | 2000 MHz |
| 15000 Mbps | Effective Memory Speed | 16000 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | Yes |
| 273 GB/s | Memory Bandwidth | 512 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 26 W | TGP | 80-140 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 3 nm | Fabrication Process | 8 nm |
| — | Die Size | 392 mm² |
| — | Transistor Count | 17.4 billion |
| — | Transistor Density | 44.39 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| No | DLSS | — |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 29, 2024 | Released | March 22, 2022 |
| Laptop | Case | Laptop |
| Professional | Purpose | Professional |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | Ampere |
| Custom | GPU Codename | GA104 |
| -Apple M4 Pro (14-Core)or above | Recommended CPU | -Intel Core i7 12800HXor above |
| 8075 | Steel Nomad Lite Score | 8802 |
| — | Time Spy | 9410 |
| 33402 | Solar Bay | 39802 |
| — | Port Royal | 6116 |
| — | Fire Strike | 25494 |
| 19523 | Wild Life Extreme | 19741 |
| — | Night Raid | 93933 |
| 500 MHz | Base Clock | 510-1035 MHz (configurable) |
| 1578 MHz | Boost Clock | 1035-1485 MHz (configurable) |
| 2560 | Shading Units | 5888 |
| 160 | Texture Mapping Units (TMUs) | 184 |
| 80 | Render Output Units (ROPs) | 96 |
| 320 | Compute Units (Pipelines) | 46 |
| — | Tensor Cores | 184 |
| — | Ray-tracing Cores | 46 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |