Quick/Comparisons
24 | Gaming | 32 |
35 | Workstation | 38 |
47 | AI/ML |
Compare with something else?
Compare Apple M5 Pro with another →| — |
100 | Energy Efficiency | 36 |
42 | Quick Comparison Final Score | — |
| Custom | Graphics Processor | TU104 (N18E-G3) |
| 2048 | Cores | 2944 |
| 128 / 64 | TMUs / ROPs | 184 / 64 |
| 3707.66 | Blender GPU | 1573.54 |
| — | Forza Horizon 5 | 76 |
| — | The Witcher 3 | 109 |
| — | Counter-Strike 2 | 148 |
| — | Far Cry 6 | 93 |
| — | Hogwarts Legacy | 59 |
| — | Call of Duty | 82 |
| — | Ghost of Tsushima | 56 |
| — | Cyberpunk 2077 | 70 |
| — | Tomb Raider | 112 |
| — | Average FPS | 89 |
| — | 1080p High | 110 |
| — | 1080p Ultra | 89 |
| — | 1440p Ultra | 65 |
| — | 4K Ultra | 37 |
| — | Margin of Error | Low |
| 75207 | GB6 Compute Score | 116500 |
| 153.3 img/sec | Background Blur | 226 img/sec |
| 101 img/sec | Face Detection | 122.4 img/sec |
| 2.82 Gpixels/sec | Horizon Detection | 4.52 Gpixels/sec |
| 4.09 Gpixels/sec | Edge Detection | 5.94 Gpixels/sec |
| 3.69 Gpixels/sec | Gaussian Blur | 6.45 Gpixels/sec |
| 0.84 Gpixels/sec | Feature Matching | 1.26 Gpixels/sec |
| 212.6 Gpixels/sec | Stereo Matching | 446.2 Gpixels/sec |
| 9757.6 FPS | Particle Physics | 14128.8 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 15014 |
| — | G2D Mark | 804 |
| — | DirectX 11 | 139 FPS |
| — | DirectX 12 | 53 FPS |
| — | GPU Compute | 6463 Ops/s |
| 18459 | GB6 ML Single Precision | — |
| 32720 | GB6 ML Half Precision | — |
| 31852 | GB6 ML Quantized | — |
| 8260 | Image Classification (SP) | — |
| 25244 | Image Segmentation (HP) | — |
| 33177 | Image Super Resolution (Q) | — |
| 51773 | Face Detection (HP) | — |
| 190718 | Pose Estimation (Q) | — |
| 2913 | Text Classification (SP) | — |
| 8985 | Machine Translation (HP) | — |
| 7777 | Object Detection (SP) | — |
| 63837 | Depth Estimation (Q) | — |
| 128419 | Style Transfer (SP) | — |
| Core ML | Framework | — |
| GPU | Backend | — |
| 104 GPixel/s | Pixel Fill Rate | 102 GPixel/s |
| 207 GTexel/s | Texture Fill Rate | 293 GTexel/s |
| 6.6 TFLOPS | FLOPS (FP32) | 9.4 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| 9600 MHz | Memory Clock | 1500 MHz |
| — | Effective Memory Speed | 12000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 307 GB/s | Memory Bandwidth | 384 GB/s |
| Custom | Interface | PCIe 3.0 x16 |
| — | TGP | 150 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 12 nm |
| — | Die Size | 545 mm² |
| 28 billion | Transistor Count | 13.6 billion |
| — | Transistor Density | 24.95 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 1.2 |
| — | CUDA | 7.5 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| — | DisplayPort | 1.4 |
| Integrated | Build | Discrete |
| March 3, 2026 | Released | January 29, 2019 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | Turing |
| Custom | GPU Codename | TU104 (N18E-G3) |
| -Apple M5 Pro (15-Core)or above | Recommended CPU | -Intel Core i7 9750Hor above |
| Apple | Vendor | Nvidia |
| 8594 | Steel Nomad Lite Score | 9737 |
| — | Time Spy | 10053 |
| 39437 | Solar Bay | 44509 |
| — | Port Royal | 6007 |
| — | Fire Strike | 25924 |
| 19874 | Wild Life Extreme | 20417 |
| — | Night Raid | 95965 |
| — | Base Clock | 1380 MHz |
| 1620 MHz | Boost Clock | 1590 MHz |
| 2048 | Shading Units | 2944 |
| 128 | Texture Mapping Units (TMUs) | 184 |
| 64 | Render Output Units (ROPs) | 64 |
| 256 | Compute Units (Pipelines) | 46 |
| — | Tensor Cores | 368 |
| — | Ray-tracing Cores | 46 |
| — | L1 Cache | 64KB per cluster |
| — | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |