Quick/Comparisons
50 | Gaming | 15 |
59 | Workstation | 25 |
41 | AI/ML |
Compare with something else?
Compare Apple M3 Ultra with another →21 |
61 | Energy Efficiency | 95 |
52 | Quick Comparison Final Score | 32 |
| Custom | Graphics Processor | Custom |
| 10240 | Cores | 1280 |
| 640 / 320 | TMUs / ROPs | 80 / 40 |
| 7360.18 | Blender GPU | 1062.09 |
| — | Forza Horizon 5 | — |
| — | The Witcher 3 | — |
| — | Counter-Strike 2 | — |
| — | Far Cry 6 | — |
| — | Hogwarts Legacy | — |
| — | Call of Duty | — |
| — | Ghost of Tsushima | — |
| — | Cyberpunk 2077 | — |
| — | Tomb Raider | — |
| — | Average FPS | — |
| — | 1080p High | — |
| — | 1080p Ultra | — |
| — | 1440p Ultra | — |
| — | 4K Ultra | — |
| — | Margin of Error | — |
| 147719 | GB6 Compute Score | 37678 |
| 204.5 img/sec | Background Blur | 72.2 img/sec |
| 126 img/sec | Face Detection | 48.3 img/sec |
| 6.53 Gpixels/sec | Horizon Detection | 1.4 Gpixels/sec |
| 10.7 Gpixels/sec | Edge Detection | 1.94 Gpixels/sec |
| 9.5 Gpixels/sec | Gaussian Blur | 1.5 Gpixels/sec |
| 1.05 Gpixels/sec | Feature Matching | 0.53 Gpixels/sec |
| 560.3 Gpixels/sec | Stereo Matching | 123.3 Gpixels/sec |
| 25267.8 FPS | Particle Physics | 4938.4 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | — |
| — | G2D Mark | — |
| — | DirectX 11 | — |
| — | DirectX 12 | — |
| — | GPU Compute | — |
| 21356 | GB6 ML Single Precision | 10346 |
| 23530 | GB6 ML Half Precision | 11883 |
| 21706 | GB6 ML Quantized | 11036 |
| 8094 | Image Classification (SP) | 4874 |
| 24595 | Image Segmentation (HP) | 8168 |
| 25190 | Image Super Resolution (Q) | 11983 |
| 38337 | Face Detection (HP) | 17036 |
| 111021 | Pose Estimation (Q) | 31171 |
| 2786 | Text Classification (SP) | 2964 |
| 4339 | Machine Translation (HP) | 3410 |
| 7668 | Object Detection (SP) | 5112 |
| 37488 | Depth Estimation (Q) | 22700 |
| 244483 | Style Transfer (SP) | 60872 |
| Core ML | Framework | Core ML |
| GPU | Backend | GPU |
| 442 GPixel/s | Pixel Fill Rate | 59 GPixel/s |
| 883 GTexel/s | Texture Fill Rate | 118 GTexel/s |
| 28.3 TFLOPS | FLOPS (FP32) | 3.8 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| 6400 MHz | Memory Clock | 7500 MHz |
| — | Effective Memory Speed | 15000 Mbps |
| 1024-bit | Bus | 128-bit |
| No | ECC | No |
| 819.3 GB/s | Memory Bandwidth | 120 GB/s |
| Custom | Interface | Custom |
| 140 W | TGP | 18 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 3 nm |
| — | Die Size | — |
| 184 billion | Transistor Count | 28 billion |
| — | Transistor Density | — |
| — | DirectX | — |
| — | Vulkan | — |
| — | OpenGL | — |
| — | OpenCL | — |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | — |
| Apple | Vendor | Apple |
| Integrated | Build | Integrated |
| March 5, 2025 | Released | May 7, 2024 |
| Desktop | Case | Laptop |
| Professional | Purpose | Professional |
| High-end | Segment | Mid-range |
| Apple M GPU | Architecture | Apple M GPU |
| Custom | GPU Codename | Custom |
| -Apple M3 Ultraor above | Recommended CPU | -Apple M4 (10-Core)or above |
| 19491 | Steel Nomad Lite Score | 4097 |
| — | Time Spy | — |
| 73690 | Solar Bay | 16545 |
| — | Port Royal | — |
| — | Fire Strike | — |
| 44759 | Wild Life Extreme | 9591 |
| — | Night Raid | — |
| — | Base Clock | 500 MHz |
| 1380 MHz | Boost Clock | 1470 MHz |
| 10240 | Shading Units | 1280 |
| 640 | Texture Mapping Units (TMUs) | 80 |
| 320 | Render Output Units (ROPs) | 40 |
| 1280 | Compute Units (Pipelines) | 160 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | — |
| — | L1 Cache | — |
| — | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |