Quick/Comparisons
50 | Gaming | 54 |
59 | Workstation | 55 |
41 | AI/ML |
Compare with something else?
Compare Apple M3 Ultra with another →48 |
61 | Energy Efficiency | 44 |
52 | Quick Comparison Final Score | 53 |
| Custom | Graphics Processor | AD104 |
| 10240 | Cores | 5888 |
| 640 / 320 | TMUs / ROPs | 184 / 64 |
| 7360.18 | Blender GPU | 5394.14 |
| — | Forza Horizon 5 | 114 |
| — | The Witcher 3 | 163 |
| — | Counter-Strike 2 | 202 |
| — | Far Cry 6 | 135 |
| — | Hogwarts Legacy | 96 |
| — | Call of Duty | 143 |
| — | Ghost of Tsushima | 89 |
| — | Cyberpunk 2077 | 115 |
| — | Tomb Raider | 196 |
| — | Average FPS | 139 |
| — | 1080p High | 165 |
| — | 1080p Ultra | 139 |
| — | 1440p Ultra | 107 |
| — | 4K Ultra | 63 |
| — | Margin of Error | Low |
| 147719 | GB6 Compute Score | 167522 |
| 204.5 img/sec | Background Blur | 233 img/sec |
| 126 img/sec | Face Detection | 141.7 img/sec |
| 6.53 Gpixels/sec | Horizon Detection | 6.62 Gpixels/sec |
| 10.7 Gpixels/sec | Edge Detection | 9.19 Gpixels/sec |
| 9.5 Gpixels/sec | Gaussian Blur | 9.2 Gpixels/sec |
| 1.05 Gpixels/sec | Feature Matching | 1.78 Gpixels/sec |
| 560.3 Gpixels/sec | Stereo Matching | 845.4 Gpixels/sec |
| 25267.8 FPS | Particle Physics | 25043.9 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 26921 |
| — | G2D Mark | 1168 |
| — | DirectX 11 | 243 FPS |
| — | DirectX 12 | 103 FPS |
| — | GPU Compute | 14623 Ops/s |
| 21356 | GB6 ML Single Precision | 27166 |
| 23530 | GB6 ML Half Precision | 40963 |
| 21706 | GB6 ML Quantized | 20332 |
| 8094 | Image Classification (SP) | 10246 |
| 24595 | Image Segmentation (HP) | 26153 |
| 25190 | Image Super Resolution (Q) | 32054 |
| 38337 | Face Detection (HP) | 51337 |
| 111021 | Pose Estimation (Q) | 124617 |
| 2786 | Text Classification (SP) | 3703 |
| 4339 | Machine Translation (HP) | 5484 |
| 7668 | Object Detection (SP) | 13134 |
| 37488 | Depth Estimation (Q) | 50548 |
| 244483 | Style Transfer (SP) | 263477 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 442 GPixel/s | Pixel Fill Rate | 158 GPixel/s |
| 883 GTexel/s | Texture Fill Rate | 455 GTexel/s |
| 28.3 TFLOPS | FLOPS (FP32) | 29.1 TFLOPS |
| System Shared | Memory Type | GDDR6X |
| — | Memory Size | 12 GB |
| 6400 MHz | Memory Clock | 1313 MHz |
| — | Effective Memory Speed | 21000 Mbps |
| 1024-bit | Bus | 192-bit |
| No | ECC | No |
| 819.3 GB/s | Memory Bandwidth | 504 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 140 W | TGP | 200 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | 294 mm² |
| 184 billion | Transistor Count | 35 billion |
| — | Transistor Density | 119.05 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 3 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| March 5, 2025 | Released | April 13, 2023 |
| Desktop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Apple M GPU | Architecture | Ada Lovelace |
| Custom | GPU Codename | AD104 |
| -Apple M3 Ultraor above | Recommended CPU | -Intel Core i7 14700Kor above |
| 19491 | Steel Nomad Lite Score | 18089 |
| — | Time Spy | 17806 |
| 73690 | Solar Bay | 82784 |
| — | Port Royal | 11154 |
| — | Fire Strike | 44075 |
| 44759 | Wild Life Extreme | 35470 |
| — | Night Raid | 153508 |
| — | Base Clock | 1920 MHz |
| 1380 MHz | Boost Clock | 2475 MHz |
| 10240 | Shading Units | 5888 |
| 640 | Texture Mapping Units (TMUs) | 184 |
| 320 | Render Output Units (ROPs) | 64 |
| 1280 | Compute Units (Pipelines) | 46 |
| — | Tensor Cores | 184 |
| — | Ray-tracing Cores | 46 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 36MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |