Quick/Comparisons
31 | Gaming | 25 |
50 | Workstation | 35 |
25 | AI/ML |
Compare with something else?
Compare Apple M1 Ultra with another →24 |
59 | Energy Efficiency | 46 |
40 | Quick Comparison Final Score | 31 |
| Custom | Graphics Processor | TU106B |
| 8192 | Cores | 2304 |
| 512 / 256 | TMUs / ROPs | 144 / 64 |
| 1644.94 | Blender GPU | 1823.68 |
| — | Cyberpunk 2077 | 53 |
| — | Forza Horizon 5 | 61 |
| — | The Witcher 3 | 84 |
| — | Counter-Strike 2 | 117 |
| — | Far Cry 6 | 74 |
| — | Hogwarts Legacy | 45 |
| — | Call of Duty | 61 |
| — | Ghost of Tsushima | 42 |
| — | Tomb Raider | 84 |
| — | Average FPS | 69 |
| — | 1080p High | 87 |
| — | 1080p Ultra | 69 |
| — | 1440p Ultra | 49 |
| — | 4K Ultra | 26 |
| — | Margin of Error | Low |
| 106397 | GB6 Compute Score | 92843 |
| 157.3 img/sec | Background Blur | 159 img/sec |
| 108.7 img/sec | Face Detection | 91.2 img/sec |
| 5.07 Gpixels/sec | Horizon Detection | 3.67 Gpixels/sec |
| 10.7 Gpixels/sec | Edge Detection | 5.1 Gpixels/sec |
| 6.59 Gpixels/sec | Gaussian Blur | 5.03 Gpixels/sec |
| 0.73 Gpixels/sec | Feature Matching | 1.08 Gpixels/sec |
| 293.4 Gpixels/sec | Stereo Matching | 411.9 Gpixels/sec |
| 14154.4 FPS | Particle Physics | 10180.5 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 12357 |
| — | G2D Mark | 602 |
| — | DirectX 11 | 111 FPS |
| — | DirectX 12 | 41 FPS |
| — | GPU Compute | 4490 Ops/s |
| 13120 | GB6 ML Single Precision | 10388 |
| 14103 | GB6 ML Half Precision | 17021 |
| 13229 | GB6 ML Quantized | 7357 |
| 4834 | Image Classification (SP) | 3954 |
| 14458 | Image Segmentation (HP) | 9425 |
| 13757 | Image Super Resolution (Q) | 11209 |
| 23618 | Face Detection (HP) | 18147 |
| 80481 | Pose Estimation (Q) | 47333 |
| 2265 | Text Classification (SP) | 1546 |
| 1798 | Machine Translation (HP) | 2209 |
| 4975 | Object Detection (SP) | 4976 |
| 25755 | Depth Estimation (Q) | 18466 |
| 135609 | Style Transfer (SP) | 90152 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 332 GPixel/s | Pixel Fill Rate | 92-95 GPixel/s |
| 664 GTexel/s | Texture Fill Rate | 207-214 GTexel/s |
| 21.2 TFLOPS | FLOPS (FP32) | 6.6-6.8 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| 6400 MHz | Memory Clock | 1750 MHz |
| 12800 Mbps | Effective Memory Speed | 14000 Mbps |
| 1024-bit | Bus | 256-bit |
| No | ECC | No |
| 819.2 GB/s | Memory Bandwidth | 448 GB/s |
| Custom | Interface | PCIe 3.0 x16 |
| 120 W | TGP | 115 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 12 nm |
| — | Die Size | 445 mm² |
| 92.8 billion | Transistor Count | 10.8 billion |
| — | Transistor Density | 24.27 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 1.2 |
| — | CUDA | 7.5 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| — | DisplayPort | 1.4 |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| March 8, 2022 | Released | January 29, 2019 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| High-end | Segment | High-end |
| Apple M GPU | Architecture | Turing |
| Custom | GPU Codename | TU106B |
| -Apple M1 Ultraor above | Recommended CPU | -Intel Core i7 10750Hor above |
| 10731 | Steel Nomad Lite Score | 7234 |
| — | Time Spy | 7566 |
| 36712 | Solar Bay | 31700 |
| — | Port Royal | 4446 |
| — | Fire Strike | 19887 |
| 29343 | Wild Life Extreme | 14527 |
| — | Night Raid | 65976 |
| 450 MHz | Base Clock | 1215-1305 MHz (configurable) |
| 1296 MHz | Boost Clock | 1440-1485 MHz (configurable) |
| 8192 | Shading Units | 2304 |
| 512 | Texture Mapping Units (TMUs) | 144 |
| 256 | Render Output Units (ROPs) | 64 |
| 1024 | Compute Units (Pipelines) | 36 |
| — | Tensor Cores | 288 |
| — | Ray-tracing Cores | 36 |
| — | L1 Cache | 64KB per cluster |
| — | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |