Quick/Comparisons
31 | Gaming | 26 |
50 | Workstation | 39 |
25 | AI/ML |
Compare with something else?
Compare Apple M1 Ultra with another →29 |
59 | Energy Efficiency | 76 |
40 | Quick Comparison Final Score | 38 |
| Custom | Graphics Processor | — |
| 8192 | Cores | 4864 |
| 512 / 256 | TMUs / ROPs | 304 / 152 |
| 1644.94 | Blender GPU | 1777.05 |
| — | Cyberpunk 2077 | — |
| — | Forza Horizon 5 | — |
| — | The Witcher 3 | — |
| — | Counter-Strike 2 | — |
| — | Far Cry 6 | — |
| — | Hogwarts Legacy | — |
| — | Call of Duty | — |
| — | Ghost of Tsushima | — |
| — | Tomb Raider | — |
| — | Average FPS | — |
| — | 1080p High | — |
| — | 1080p Ultra | — |
| — | 1440p Ultra | — |
| — | 4K Ultra | — |
| — | Margin of Error | — |
| 106397 | GB6 Compute Score | 86936 |
| 157.3 img/sec | Background Blur | 149 img/sec |
| 108.7 img/sec | Face Detection | 98.1 img/sec |
| 5.07 Gpixels/sec | Horizon Detection | 3.8 Gpixels/sec |
| 10.7 Gpixels/sec | Edge Detection | 6.88 Gpixels/sec |
| 6.59 Gpixels/sec | Gaussian Blur | 4.44 Gpixels/sec |
| 0.73 Gpixels/sec | Feature Matching | 0.73 Gpixels/sec |
| 293.4 Gpixels/sec | Stereo Matching | 264.9 Gpixels/sec |
| 14154.4 FPS | Particle Physics | 11144.2 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | — |
| — | G2D Mark | — |
| — | DirectX 11 | — |
| — | DirectX 12 | — |
| — | GPU Compute | — |
| 13120 | GB6 ML Single Precision | 15005 |
| 14103 | GB6 ML Half Precision | 16456 |
| 13229 | GB6 ML Quantized | 15418 |
| 4834 | Image Classification (SP) | 6657 |
| 14458 | Image Segmentation (HP) | 13854 |
| 13757 | Image Super Resolution (Q) | 18642 |
| 23618 | Face Detection (HP) | 27965 |
| 80481 | Pose Estimation (Q) | 83144 |
| 2265 | Text Classification (SP) | 2377 |
| 1798 | Machine Translation (HP) | 2052 |
| 4975 | Object Detection (SP) | 6495 |
| 25755 | Depth Estimation (Q) | 31105 |
| 135609 | Style Transfer (SP) | 135686 |
| Core ML | Framework | Core ML |
| GPU | Backend | GPU |
| 332 GPixel/s | Pixel Fill Rate | 212 GPixel/s |
| 664 GTexel/s | Texture Fill Rate | 425 GTexel/s |
| 21.2 TFLOPS | FLOPS (FP32) | 13.6 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| 6400 MHz | Memory Clock | 6400 MHz |
| 12800 Mbps | Effective Memory Speed | 12800 Mbps |
| 1024-bit | Bus | 512-bit |
| No | ECC | No |
| 819.2 GB/s | Memory Bandwidth | 409.6 GB/s |
| Custom | Interface | Custom |
| 120 W | TGP | 70 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| — | Die Size | — |
| 92.8 billion | Transistor Count | 52 billion |
| — | Transistor Density | — |
| — | DirectX | — |
| — | Vulkan | — |
| — | OpenGL | — |
| — | OpenCL | — |
| — | CUDA | — |
| No | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | — |
| Apple | Vendor | Apple |
| Integrated | Build | Integrated |
| March 8, 2022 | Released | January 17, 2023 |
| Laptop | Case | Laptop |
| Professional | Purpose | Professional |
| High-end | Segment | High-end |
| Apple M GPU | Architecture | Apple M GPU |
| Custom | GPU Codename | — |
| -Apple M1 Ultraor above | Recommended CPU | — |
| 10731 | Steel Nomad Lite Score | 9413 |
| — | Time Spy | — |
| 36712 | Solar Bay | 30427 |
| — | Port Royal | — |
| — | Fire Strike | — |
| 29343 | Wild Life Extreme | 24969 |
| — | Night Raid | — |
| 450 MHz | Base Clock | 450 MHz |
| 1296 MHz | Boost Clock | 1398 MHz |
| 8192 | Shading Units | 4864 |
| 512 | Texture Mapping Units (TMUs) | 304 |
| 256 | Render Output Units (ROPs) | 152 |
| 1024 | Compute Units (Pipelines) | 608 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | — |
| — | L1 Cache | — |
| — | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |