Quick/Comparisons
14 | Gaming | 28 |
24 | Workstation | 29 |
| — | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →97 | Energy Efficiency | 66 |
32 | Quick Comparison Final Score | 35 |
| Custom | Graphics Processor | Strix Halo |
| 1024 | Cores | 2048 |
| 64 / 32 | TMUs / ROPs | 128 / 64 |
| 1060.26 | Blender GPU | 1188.98 |
| — | Forza Horizon 5 | 70 |
| — | The Witcher 3 | 94 |
| — | Counter-Strike 2 | 123 |
| — | Far Cry 6 | 85 |
| — | Hogwarts Legacy | 55 |
| — | Call of Duty | 83 |
| — | Ghost of Tsushima | 56 |
| — | Cyberpunk 2077 | 61 |
| — | Tomb Raider | 103 |
| — | Average FPS | 81 |
| — | 1080p High | 104 |
| — | 1080p Ultra | 81 |
| — | 1440p Ultra | 57 |
| — | 4K Ultra | 31 |
| — | Margin of Error | Medium |
| 30791 | GB6 Compute Score | 81081 |
| 57.4 img/sec | Background Blur | 201.1 img/sec |
| 41.3 img/sec | Face Detection | 104.8 img/sec |
| 1.21 Gpixels/sec | Horizon Detection | 2.53 Gpixels/sec |
| 1.74 Gpixels/sec | Edge Detection | 3.37 Gpixels/sec |
| 1.12 Gpixels/sec | Gaussian Blur | 3.12 Gpixels/sec |
| 0.43 Gpixels/sec | Feature Matching | 0.93 Gpixels/sec |
| 94.9 Gpixels/sec | Stereo Matching | 327.5 Gpixels/sec |
| 3902.5 FPS | Particle Physics | 12215.6 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 16166 |
| — | G2D Mark | 1109 |
| — | DirectX 11 | 148 FPS |
| — | DirectX 12 | 70 FPS |
| — | GPU Compute | 7513 Ops/s |
| — | GB6 ML Single Precision | 18145 |
| — | GB6 ML Half Precision | 22099 |
| — | GB6 ML Quantized | 14884 |
| — | Image Classification (SP) | 9259 |
| — | Image Segmentation (HP) | 11219 |
| — | Image Super Resolution (Q) | 19775 |
| — | Face Detection (HP) | 31987 |
| — | Pose Estimation (Q) | 62399 |
| — | Text Classification (SP) | 3757 |
| — | Machine Translation (HP) | 6121 |
| — | Object Detection (SP) | 6979 |
| — | Depth Estimation (Q) | 35735 |
| — | Style Transfer (SP) | 129996 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 47 GPixel/s | Pixel Fill Rate | 179 GPixel/s |
| 94 GTexel/s | Texture Fill Rate | 358 GTexel/s |
| 3 TFLOPS | FLOPS (FP32) | 11.5 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 | PCIe 5.0 x16 |
| 15 W | TGP | 45-120 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 4 nm |
| — | Die Size | 308 mm² |
| — | Transistor Count | — |
| — | Transistor Density | — |
| — | DirectX | 12.2 |
| — | Vulkan | 1.4 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.1 |
| — | CUDA | No |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1a |
| Apple | Vendor | Amd |
| Integrated | Build | Integrated |
| October 29, 2024 | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | RDNA 3.5 |
| Custom | GPU Codename | Strix Halo |
| -Apple M4 (8-Core)or above | Recommended CPU | -AMD Ryzen AI Max 385or above |
| 3450 | Steel Nomad Lite Score | 8570 |
| — | Time Spy | 9171 |
| 13908 | Solar Bay | 41112 |
| — | Port Royal | 5181 |
| — | Fire Strike | 24607 |
| 7928 | Wild Life Extreme | 18225 |
| — | Night Raid | 98347 |
| 500 MHz | Base Clock | 1295 MHz |
| 1470 MHz | Boost Clock | 2800 MHz |
| 1024 | Shading Units | 2048 |
| 64 | Texture Mapping Units (TMUs) | 128 |
| 32 | Render Output Units (ROPs) | 64 |
| 128 | Compute Units (Pipelines) | 32 |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | 32 |
| — | L1 Cache | 512KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |