Quick/Comparisons
50 | Gaming | 4 |
59 | Workstation | 13 |
41 | AI/ML |
Compare with something else?
Compare Apple M3 Ultra with another →4 |
61 | Energy Efficiency | 79 |
52 | Quick Comparison Final Score | 19 |
| Custom | Graphics Processor | Tiger Lake GT2 |
| 10240 | Cores | 640 |
| 640 / 320 | TMUs / ROPs | 40 / 20 |
| 7360.18 | Blender GPU | — |
| — | Forza Horizon 5 | 11 |
| — | The Witcher 3 | 10 |
| — | Counter-Strike 2 | 12 |
| — | Far Cry 6 | 9 |
| — | Hogwarts Legacy | - |
| — | Call of Duty | 11 |
| — | Ghost of Tsushima | - |
| — | Cyberpunk 2077 | — |
| — | Tomb Raider | 11 |
| — | Average FPS | 9 |
| — | 1080p High | 12 |
| — | 1080p Ultra | 9 |
| — | 1440p Ultra | - |
| — | 4K Ultra | - |
| — | Margin of Error | Medium |
| 147719 | GB6 Compute Score | 14240 |
| 204.5 img/sec | Background Blur | 31 img/sec |
| 126 img/sec | Face Detection | 23.3 img/sec |
| 6.53 Gpixels/sec | Horizon Detection | 0.61 Gpixels/sec |
| 10.7 Gpixels/sec | Edge Detection | 0.87 Gpixels/sec |
| 9.5 Gpixels/sec | Gaussian Blur | 0.36 Gpixels/sec |
| 1.05 Gpixels/sec | Feature Matching | 0.15 Gpixels/sec |
| 560.3 Gpixels/sec | Stereo Matching | 36.1 Gpixels/sec |
| 25267.8 FPS | Particle Physics | 2493.2 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 2608 |
| — | G2D Mark | 391 |
| — | DirectX 11 | 16 FPS |
| — | DirectX 12 | 12 FPS |
| — | GPU Compute | 1184 Ops/s |
| 21356 | GB6 ML Single Precision | 2754 |
| 23530 | GB6 ML Half Precision | 2688 |
| 21706 | GB6 ML Quantized | 1643 |
| 8094 | Image Classification (SP) | 1149 |
| 24595 | Image Segmentation (HP) | 1796 |
| 25190 | Image Super Resolution (Q) | 1394 |
| 38337 | Face Detection (HP) | 2775 |
| 111021 | Pose Estimation (Q) | 5476 |
| 2786 | Text Classification (SP) | 981 |
| 4339 | Machine Translation (HP) | 905 |
| 7668 | Object Detection (SP) | 1277 |
| 37488 | Depth Estimation (Q) | 3737 |
| 244483 | Style Transfer (SP) | 22348 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 442 GPixel/s | Pixel Fill Rate | 17-30 GPixel/s |
| 883 GTexel/s | Texture Fill Rate | 34-60 GTexel/s |
| 28.3 TFLOPS | FLOPS (FP32) | 1.1-1.9 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | System RAM Dependent |
| 6400 MHz | Memory Clock | System RAM Dependent |
| — | Effective Memory Speed | System RAM Dependent |
| 1024-bit | Bus | — |
| No | ECC | No |
| 819.3 GB/s | Memory Bandwidth | — |
| Custom | Interface | Ring Bus |
| 140 W | TGP | 15 W |
| TSMC | Manufacturing | Intel |
| 3 nm | Fabrication Process | 10 nm |
| — | Die Size | 146 mm² |
| 184 billion | Transistor Count | — |
| — | Transistor Density | — |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | — |
| Apple | Vendor | Intel |
| Integrated | Build | Integrated |
| March 5, 2025 | Released | August 15, 2020 |
| Desktop | Case | Laptop |
| Professional | Purpose | Generic |
| High-end | Segment | Entry-level |
| Apple M GPU | Architecture | Generation 12.1 |
| Custom | GPU Codename | Tiger Lake GT2 |
| -Apple M3 Ultraor above | Recommended CPU | -Intel Core i5 1130G7or above |
| 19491 | Steel Nomad Lite Score | 849 |
| — | Time Spy | 1229 |
| 73690 | Solar Bay | — |
| — | Port Royal | — |
| — | Fire Strike | 4195 |
| 44759 | Wild Life Extreme | 2124 |
| — | Night Raid | 15167 |
| — | Base Clock | 300 MHz |
| 1380 MHz | Boost Clock | 850-1500 MHz (configurable) |
| 10240 | Shading Units | 640 |
| 640 | Texture Mapping Units (TMUs) | 40 |
| 320 | Render Output Units (ROPs) | 20 |
| 1280 | Compute Units (Pipelines) | 80 |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | No |
| — | L1 Cache | — |
| — | L2 Cache | 1024KB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |