Quick/Comparisons
50 | Gaming | 34 |
59 | Workstation | 36 |
41 | AI/ML |
Compare with something else?
Compare Apple M3 Ultra with another →30 |
61 | Energy Efficiency | 47 |
52 | Quick Comparison Final Score | 36 |
| Custom | Graphics Processor | Navi 22 |
| 10240 | Cores | 2560 |
| 640 / 320 | TMUs / ROPs | 160 / 64 |
| 7360.18 | Blender GPU | 1394.16 |
| — | Forza Horizon 5 | 82 |
| — | The Witcher 3 | 113 |
| — | Counter-Strike 2 | 147 |
| — | Far Cry 6 | 102 |
| — | Hogwarts Legacy | 67 |
| — | Call of Duty | 102 |
| — | Ghost of Tsushima | 69 |
| — | Cyberpunk 2077 | 72 |
| — | Tomb Raider | 121 |
| — | Average FPS | 97 |
| — | 1080p High | 120 |
| — | 1080p Ultra | 97 |
| — | 1440p Ultra | 69 |
| — | 4K Ultra | 37 |
| — | Margin of Error | Low |
| 147719 | GB6 Compute Score | 99418 |
| 204.5 img/sec | Background Blur | 222.9 img/sec |
| 126 img/sec | Face Detection | 135.3 img/sec |
| 6.53 Gpixels/sec | Horizon Detection | 3.46 Gpixels/sec |
| 10.7 Gpixels/sec | Edge Detection | 5.14 Gpixels/sec |
| 9.5 Gpixels/sec | Gaussian Blur | 3.64 Gpixels/sec |
| 1.05 Gpixels/sec | Feature Matching | 0.92 Gpixels/sec |
| 560.3 Gpixels/sec | Stereo Matching | 432.6 Gpixels/sec |
| 25267.8 FPS | Particle Physics | 13677.6 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 13236 |
| — | G2D Mark | 532 |
| — | DirectX 11 | 127 FPS |
| — | DirectX 12 | 65 FPS |
| — | GPU Compute | 5050 Ops/s |
| 21356 | GB6 ML Single Precision | 17087 |
| 23530 | GB6 ML Half Precision | 18189 |
| 21706 | GB6 ML Quantized | 13247 |
| 8094 | Image Classification (SP) | 7861 |
| 24595 | Image Segmentation (HP) | 7803 |
| 25190 | Image Super Resolution (Q) | 21982 |
| 38337 | Face Detection (HP) | 23070 |
| 111021 | Pose Estimation (Q) | 93148 |
| 2786 | Text Classification (SP) | 2165 |
| 4339 | Machine Translation (HP) | 3022 |
| 7668 | Object Detection (SP) | 8375 |
| 37488 | Depth Estimation (Q) | 31430 |
| 244483 | Style Transfer (SP) | 178071 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 442 GPixel/s | Pixel Fill Rate | 147 GPixel/s |
| 883 GTexel/s | Texture Fill Rate | 368 GTexel/s |
| 28.3 TFLOPS | FLOPS (FP32) | 11.8 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 12 GB |
| 6400 MHz | Memory Clock | 1750 MHz |
| — | Effective Memory Speed | 14000 Mbps |
| 1024-bit | Bus | 192-bit |
| No | ECC | No |
| 819.3 GB/s | Memory Bandwidth | 336 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 140 W | TGP | 145 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 7 nm |
| — | Die Size | 335 mm² |
| 184 billion | Transistor Count | 17.2 billion |
| — | Transistor Density | 51.34 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 1.4 |
| Apple | Vendor | Amd |
| Integrated | Build | Discrete |
| March 5, 2025 | Released | June 1, 2021 |
| Desktop | Case | Laptop |
| Professional | Purpose | Gaming |
| High-end | Segment | High-end |
| Apple M GPU | Architecture | RDNA 2.0 |
| Custom | GPU Codename | Navi 22 |
| -Apple M3 Ultraor above | Recommended CPU | -AMD Ryzen 9 5900HXor above |
| 19491 | Steel Nomad Lite Score | 10120 |
| — | Time Spy | 11506 |
| 73690 | Solar Bay | 44266 |
| — | Port Royal | 5558 |
| — | Fire Strike | 33464 |
| 44759 | Wild Life Extreme | 18898 |
| — | Night Raid | 77742 |
| — | Base Clock | 2116 MHz |
| 1380 MHz | Boost Clock | 2300 MHz |
| 10240 | Shading Units | 2560 |
| 640 | Texture Mapping Units (TMUs) | 160 |
| 320 | Render Output Units (ROPs) | 64 |
| 1280 | Compute Units (Pipelines) | 40 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 40 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 3MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |