Quick/Comparisons
15 | Gaming | 16 |
25 | Workstation | 10 |
21 | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →7 |
95 | Energy Efficiency | 94 |
32 | Quick Comparison Final Score | 26 |
| Custom | Graphics Processor | — |
| 1280 | Cores | 512 |
| 80 / 40 | TMUs / ROPs | 32 / 16 |
| 1062.09 | Blender GPU | — |
| — | Tomb Raider | — |
| — | Average FPS | — |
| — | Forza Horizon 5 | — |
| — | The Witcher 3 | — |
| — | Counter-Strike 2 | — |
| — | Far Cry 6 | — |
| — | Hogwarts Legacy | — |
| — | Call of Duty | — |
| — | Ghost of Tsushima | — |
| — | Cyberpunk 2077 | — |
| — | 1080p High | — |
| — | 1080p Ultra | — |
| — | 1440p Ultra | — |
| — | 4K Ultra | — |
| — | Margin of Error | — |
| 37678 | GB6 Compute Score | 16321 |
| 72.2 img/sec | Background Blur | 37.6 img/sec |
| 48.3 img/sec | Face Detection | 17.2 img/sec |
| 1.4 Gpixels/sec | Horizon Detection | 0.3 Gpixels/sec |
| 1.94 Gpixels/sec | Edge Detection | 0.63 Gpixels/sec |
| 1.5 Gpixels/sec | Gaussian Blur | 0.94 Gpixels/sec |
| 0.53 Gpixels/sec | Feature Matching | 0.22 Gpixels/sec |
| 123.3 Gpixels/sec | Stereo Matching | 60 Gpixels/sec |
| 4938.4 FPS | Particle Physics | 3695.9 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | — |
| — | G2D Mark | — |
| — | DirectX 11 | — |
| — | DirectX 12 | — |
| — | GPU Compute | — |
| 10346 | GB6 ML Single Precision | 3770 |
| 11883 | GB6 ML Half Precision | 5146 |
| 11036 | GB6 ML Quantized | 2824 |
| 4874 | Image Classification (SP) | 2902 |
| 8168 | Image Segmentation (HP) | 5473 |
| 11983 | Image Super Resolution (Q) | 2967 |
| 17036 | Face Detection (HP) | 6068 |
| 31171 | Pose Estimation (Q) | 8220 |
| 2964 | Text Classification (SP) | 609 |
| 3410 | Machine Translation (HP) | 1146 |
| 5112 | Object Detection (SP) | 2766 |
| 22700 | Depth Estimation (Q) | 6405 |
| 60872 | Style Transfer (SP) | 26796 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 59 GPixel/s | Pixel Fill Rate | 28-32 GPixel/s |
| 118 GTexel/s | Texture Fill Rate | 56-64 GTexel/s |
| 3.8 TFLOPS | FLOPS (FP32) | 1.8-2 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| 7500 MHz | Memory Clock | — |
| 15000 Mbps | Effective Memory Speed | — |
| 128-bit | Bus | — |
| No | ECC | — |
| 120 GB/s | Memory Bandwidth | — |
| Custom | Interface | Ring Bus |
| 18 W | TGP | 14 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | — |
| 28 billion | Transistor Count | — |
| — | Transistor Density | — |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1 |
| Apple | Vendor | Intel |
| Integrated | Build | Integrated |
| May 7, 2024 | Released | December 14, 2023 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Xe LPG |
| Custom | GPU Codename | — |
| -Apple M4 (10-Core)or above | Recommended CPU | -Intel Core Ultra 5 125Uor above |
| 4097 | Steel Nomad Lite Score | — |
| — | Time Spy | — |
| 16545 | Solar Bay | — |
| — | Port Royal | — |
| — | Fire Strike | — |
| 9591 | Wild Life Extreme | — |
| — | Night Raid | — |
| 500 MHz | Base Clock | 300 MHz |
| 1470 MHz | Boost Clock | 1750-2000 MHz (configurable) |
| 1280 | Shading Units | 512 |
| 80 | Texture Mapping Units (TMUs) | 32 |
| 40 | Render Output Units (ROPs) | 16 |
| 160 | Compute Units (Pipelines) | 64 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 4 |
| — | L1 Cache | 768KB shared |
| — | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |