Quick/Comparisons
14 | Gaming | 11 |
24 | Workstation | 15 |
| — | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →97 | Energy Efficiency | 89 |
32 | Quick Comparison Final Score | 25 |
| Custom | Graphics Processor | Arrow Lake iGPU |
| 1024 | Cores | 896 |
| 64 / 32 | TMUs / ROPs | 56 / 28 |
| 1060.26 | Blender GPU | 640.3 |
| — | Forza Horizon 5 | 25 |
| — | The Witcher 3 | 31 |
| — | Counter-Strike 2 | 25 |
| — | Far Cry 6 | 32 |
| — | Hogwarts Legacy | 12 |
| — | Call of Duty | 28 |
| — | Ghost of Tsushima | 15 |
| — | Cyberpunk 2077 | 18 |
| — | Tomb Raider | 31 |
| — | Average FPS | 24 |
| — | 1080p High | 32 |
| — | 1080p Ultra | 24 |
| — | 1440p Ultra | 18 |
| — | 4K Ultra | - |
| — | Margin of Error | Low |
| 30791 | GB6 Compute Score | 36282 |
| 57.4 img/sec | Background Blur | 70.9 img/sec |
| 41.3 img/sec | Face Detection | 34.9 img/sec |
| 1.21 Gpixels/sec | Horizon Detection | 1.13 Gpixels/sec |
| 1.74 Gpixels/sec | Edge Detection | 1.42 Gpixels/sec |
| 1.12 Gpixels/sec | Gaussian Blur | 1.96 Gpixels/sec |
| 0.43 Gpixels/sec | Feature Matching | 0.45 Gpixels/sec |
| 94.9 Gpixels/sec | Stereo Matching | 131.5 Gpixels/sec |
| 3902.5 FPS | Particle Physics | 7360.9 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 6157 |
| — | G2D Mark | 793 |
| — | DirectX 11 | 43 FPS |
| — | DirectX 12 | 27 FPS |
| — | GPU Compute | 2702 Ops/s |
| — | GB6 ML Single Precision | 7262 |
| — | GB6 ML Half Precision | 9964 |
| — | GB6 ML Quantized | 5008 |
| — | Image Classification (SP) | 3978 |
| — | Image Segmentation (HP) | 8374 |
| — | Image Super Resolution (Q) | 5792 |
| — | Face Detection (HP) | 13023 |
| — | Pose Estimation (Q) | 16149 |
| — | Text Classification (SP) | 1356 |
| — | Machine Translation (HP) | 2594 |
| — | Object Detection (SP) | 4754 |
| — | Depth Estimation (Q) | 12040 |
| — | Style Transfer (SP) | 51653 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 47 GPixel/s | Pixel Fill Rate | 62 GPixel/s |
| 94 GTexel/s | Texture Fill Rate | 123 GTexel/s |
| 3 TFLOPS | FLOPS (FP32) | 3.9 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 4.0 x8 |
| 15 W | TGP | 35 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | — |
| — | Transistor Count | — |
| — | Transistor Density | — |
| — | DirectX | 12.2 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | No |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1 |
| Apple | Vendor | Intel |
| Integrated | Build | Integrated |
| October 29, 2024 | Released | January 6, 2025 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Apple M GPU | Architecture | Xe+ |
| Custom | GPU Codename | Arrow Lake iGPU |
| -Apple M4 (8-Core)or above | Recommended CPU | -Intel Core Ultra 5 225Hor above |
| 3450 | Steel Nomad Lite Score | 2921 |
| — | Time Spy | 3407 |
| 13908 | Solar Bay | 12731 |
| — | Port Royal | 1902 |
| — | Fire Strike | 8020 |
| 7928 | Wild Life Extreme | 5985 |
| — | Night Raid | 37233 |
| 500 MHz | Base Clock | 300 MHz |
| 1470 MHz | Boost Clock | 2200 MHz |
| 1024 | Shading Units | 896 |
| 64 | Texture Mapping Units (TMUs) | 56 |
| 32 | Render Output Units (ROPs) | 28 |
| 128 | Compute Units (Pipelines) | 7 |
| — | Tensor Cores | 112 |
| — | Ray-tracing Cores | 7 |
| — | L1 Cache | — |
| — | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |