Quick/Comparisons
19 | Gaming | 43 |
32 | Workstation | 53 |
34 | AI/ML |
Compare with something else?
Compare Apple M5 GPU with another →39 |
100 | Energy Efficiency | 56 |
38 | Quick Comparison Final Score | 47 |
| Custom | Graphics Processor | AD104 |
| 1280 | Cores | 5120 |
| 80 / 40 | TMUs / ROPs | 160 / 64 |
| 264.45 | Blender GPU | 4377.08 |
| — | Forza Horizon 5 | 93 |
| — | The Witcher 3 | 134 |
| — | Counter-Strike 2 | 191 |
| — | Far Cry 6 | 113 |
| — | Hogwarts Legacy | 80 |
| — | Call of Duty | 111 |
| — | Ghost of Tsushima | 72 |
| — | Cyberpunk 2077 | 89 |
| — | Tomb Raider | 145 |
| — | Average FPS | 114 |
| — | 1080p High | 138 |
| — | 1080p Ultra | 114 |
| — | 1440p Ultra | 84 |
| — | 4K Ultra | 49 |
| — | Margin of Error | High |
| 75777 | GB6 Compute Score | 131037 |
| — | Background Blur | 223 img/sec |
| — | Face Detection | 145.8 img/sec |
| — | Horizon Detection | 5.87 Gpixels/sec |
| — | Edge Detection | 7.77 Gpixels/sec |
| — | Gaussian Blur | 7.2 Gpixels/sec |
| — | Feature Matching | 1.39 Gpixels/sec |
| — | Stereo Matching | 458.7 Gpixels/sec |
| — | Particle Physics | 14313 FPS |
| — | API | OpenCL |
| — | G3D Mark Score | 19719 |
| — | G2D Mark | 712 |
| — | DirectX 11 | 187 FPS |
| — | DirectX 12 | 83 FPS |
| — | GPU Compute | 7623 Ops/s |
| 13289 | GB6 ML Single Precision | 20783 |
| 24800 | GB6 ML Half Precision | 33871 |
| 23572 | GB6 ML Quantized | 16429 |
| 6348 | Image Classification (SP) | 8316 |
| 16813 | Image Segmentation (HP) | 17301 |
| 30322 | Image Super Resolution (Q) | 27105 |
| 34387 | Face Detection (HP) | 38189 |
| 111591 | Pose Estimation (Q) | 105500 |
| 2319 | Text Classification (SP) | 3319 |
| 5555 | Machine Translation (HP) | 3845 |
| 6450 | Object Detection (SP) | 10208 |
| 53195 | Depth Estimation (Q) | 38369 |
| 82314 | Style Transfer (SP) | 196359 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 65 GPixel/s | Pixel Fill Rate | 99-144 GPixel/s |
| 130 GTexel/s | Texture Fill Rate | 247-360 GTexel/s |
| 4.1 TFLOPS | FLOPS (FP32) | 15.8-23 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 12 GB |
| 9600 MHz | Memory Clock | 2250 MHz |
| — | Effective Memory Speed | 18000 Mbps |
| 128-bit | Bus | 192-bit |
| No | ECC | Yes |
| 153 GB/s | Memory Bandwidth | 432 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| — | TGP | 60-140 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | 294 mm² |
| 28 billion | Transistor Count | 35.8 billion |
| — | Transistor Density | 121.77 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 |
| October 15, 2025 | Released | March 21, 2023 |
| Laptop | Case | Laptop |
| Professional | Purpose | Professional |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Ada Lovelace |
| Custom | GPU Codename | AD104 |
| -Apple M5 (10-Core)or above | Recommended CPU | -Intel Core Ultra 7 165Hor above |
| 5337 | Steel Nomad Lite Score | 13536 |
| — | Time Spy | 12966 |
| 24534 | Solar Bay | 52474 |
| — | Port Royal | 7976 |
| — | Fire Strike | 32977 |
| 12266 | Wild Life Extreme | 26514 |
| — | Night Raid | 110011 |
| — | Base Clock | — |
| 1620 MHz | Boost Clock | 1545-2250 MHz (configurable) |
| 1280 | Shading Units | 5120 |
| 80 | Texture Mapping Units (TMUs) | 160 |
| 40 | Render Output Units (ROPs) | 64 |
| 160 | Compute Units (Pipelines) | 40 |
| — | Tensor Cores | 160 |
| — | Ray-tracing Cores | 40 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |