Quick/Comparisons
24 | Gaming | 8 |
34 | Workstation | 16 |
34 | AI/ML |
Compare with something else?
Compare Apple M4 Pro with another →6 |
94 | Energy Efficiency | 18 |
39 | Quick Comparison Final Score | 11 |
| Custom | Graphics Processor | GM206 |
| 2560 | Cores | 1024 |
| 160 / 80 | TMUs / ROPs | 64 / 32 |
| 2520.96 | Blender GPU | 170.84 |
| — | Forza Horizon 5 | 14 |
| — | The Witcher 3 | 18 |
| — | Counter-Strike 2 | 29 |
| — | Far Cry 6 | 27 |
| — | Hogwarts Legacy | 12 |
| — | Call of Duty | 24 |
| — | Ghost of Tsushima | - |
| — | Cyberpunk 2077 | 11 |
| — | Tomb Raider | 26 |
| — | Average FPS | 19 |
| — | 1080p High | 26 |
| — | 1080p Ultra | 19 |
| — | 1440p Ultra | 13 |
| — | 4K Ultra | - |
| — | Margin of Error | Low |
| 70029 | GB6 Compute Score | 20370 |
| 125.1 img/sec | Background Blur | 51.7 img/sec |
| 80 img/sec | Face Detection | 26.1 img/sec |
| 2.88 Gpixels/sec | Horizon Detection | 0.84 Gpixels/sec |
| 4.22 Gpixels/sec | Edge Detection | 1.36 Gpixels/sec |
| 2.98 Gpixels/sec | Gaussian Blur | 1.26 Gpixels/sec |
| 0.8 Gpixels/sec | Feature Matching | 0.14 Gpixels/sec |
| 235 Gpixels/sec | Stereo Matching | 64.9 Gpixels/sec |
| 9516.1 FPS | Particle Physics | 1825 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 6141 |
| — | G2D Mark | 677 |
| — | DirectX 11 | 42 FPS |
| — | DirectX 12 | 28 FPS |
| — | GPU Compute | 2801 Ops/s |
| 17327 | GB6 ML Single Precision | 3784 |
| 18455 | GB6 ML Half Precision | 3830 |
| 17831 | GB6 ML Quantized | 2724 |
| 8046 | Image Classification (SP) | 1492 |
| 15443 | Image Segmentation (HP) | 2183 |
| 20807 | Image Super Resolution (Q) | 3618 |
| 30860 | Face Detection (HP) | 3654 |
| 56783 | Pose Estimation (Q) | 11306 |
| 2888 | Text Classification (SP) | 1315 |
| 6167 | Machine Translation (HP) | 2085 |
| 7592 | Object Detection (SP) | 1927 |
| 33607 | Depth Estimation (Q) | 5491 |
| 126726 | Style Transfer (SP) | 22683 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 126 GPixel/s | Pixel Fill Rate | 38 GPixel/s |
| 252 GTexel/s | Texture Fill Rate | 75 GTexel/s |
| 8.1 TFLOPS | FLOPS (FP32) | 2.4 TFLOPS |
| System Shared | Memory Type | GDDR5 |
| — | Memory Size | 2 GB |
| 8533 MHz | Memory Clock | 1753 MHz |
| 15000 Mbps | Effective Memory Speed | 7000 Mbps |
| 192-bit | Bus | 128-bit |
| No | ECC | No |
| 273 GB/s | Memory Bandwidth | 112.2 GB/s |
| Custom | Interface | PCIe 3.0 x16 |
| 26 W | TGP | 120 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 28 nm |
| — | Die Size | 228 mm² |
| — | Transistor Count | 2 billion |
| — | Transistor Density | 8.77 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 5.2 |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | 1.2 |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 29, 2024 | Released | January 22, 2015 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Maxwell 2.0 |
| Custom | GPU Codename | GM206 |
| -Apple M4 Pro (14-Core)or above | Recommended CPU | — |
| 8075 | Steel Nomad Lite Score | 2179 |
| — | Time Spy | 2302 |
| 33402 | Solar Bay | — |
| — | Port Royal | — |
| — | Fire Strike | 7720 |
| 19523 | Wild Life Extreme | 4543 |
| — | Night Raid | 31114 |
| 500 MHz | Base Clock | 1127 MHz |
| 1578 MHz | Boost Clock | 1178 MHz |
| 2560 | Shading Units | 1024 |
| 160 | Texture Mapping Units (TMUs) | 64 |
| 80 | Render Output Units (ROPs) | 32 |
| 320 | Compute Units (Pipelines) | 8 |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | No |
| — | L1 Cache | 48KB per cluster |
| — | L2 Cache | 1MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |