Quick/Comparisons
14 | Gaming | 31 |
24 | Workstation | 32 |
| — | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →97 | Energy Efficiency | 65 |
32 | Quick Comparison Final Score | 37 |
| Custom | Graphics Processor | Navi 33 |
| 1024 | Cores | 2048 |
| 64 / 32 | TMUs / ROPs | 128 / 64 |
| 1060.26 | Blender GPU | 1021.44 |
| — | Forza Horizon 5 | 78 |
| — | The Witcher 3 | 103 |
| — | Counter-Strike 2 | 137 |
| — | Far Cry 6 | 95 |
| — | Hogwarts Legacy | 58 |
| — | Call of Duty | 89 |
| — | Ghost of Tsushima | 63 |
| — | Cyberpunk 2077 | 65 |
| — | Tomb Raider | 114 |
| — | Average FPS | 89 |
| — | 1080p High | 112 |
| — | 1080p Ultra | 89 |
| — | 1440p Ultra | 62 |
| — | 4K Ultra | 34 |
| — | Margin of Error | Low |
| 30791 | GB6 Compute Score | 75137 |
| 57.4 img/sec | Background Blur | 183.6 img/sec |
| 41.3 img/sec | Face Detection | 91.6 img/sec |
| 1.21 Gpixels/sec | Horizon Detection | 2.68 Gpixels/sec |
| 1.74 Gpixels/sec | Edge Detection | 3.95 Gpixels/sec |
| 1.12 Gpixels/sec | Gaussian Blur | 3.39 Gpixels/sec |
| 0.43 Gpixels/sec | Feature Matching | 0.84 Gpixels/sec |
| 94.9 Gpixels/sec | Stereo Matching | 244.3 Gpixels/sec |
| 3902.5 FPS | Particle Physics | 9216.4 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 15485 |
| — | G2D Mark | 765 |
| — | DirectX 11 | 137 FPS |
| — | DirectX 12 | 67 FPS |
| — | GPU Compute | 7016 Ops/s |
| — | GB6 ML Single Precision | 18185 |
| — | GB6 ML Half Precision | 23280 |
| — | GB6 ML Quantized | 14842 |
| — | Image Classification (SP) | 8076 |
| — | Image Segmentation (HP) | 10203 |
| — | Image Super Resolution (Q) | 22390 |
| — | Face Detection (HP) | 29334 |
| — | Pose Estimation (Q) | 84068 |
| — | Text Classification (SP) | 3066 |
| — | Machine Translation (HP) | 4439 |
| — | Object Detection (SP) | 7062 |
| — | Depth Estimation (Q) | 38916 |
| — | Style Transfer (SP) | 160714 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 47 GPixel/s | Pixel Fill Rate | 118-141 GPixel/s |
| 94 GTexel/s | Texture Fill Rate | 236-282 GTexel/s |
| 3 TFLOPS | FLOPS (FP32) | 15.1-18 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| 7500 MHz | Memory Clock | 2250 MHz |
| 15000 Mbps | Effective Memory Speed | 18000 Mbps |
| 128-bit | Bus | 128-bit |
| No | ECC | — |
| 120 GB/s | Memory Bandwidth | 288 GB/s |
| Custom | Interface | PCIe 4.0 x8 |
| 15 W | TGP | 75-100 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 6 nm |
| — | Die Size | 204 mm² |
| — | Transistor Count | 13.3 billion |
| — | Transistor Density | 65.2 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.2 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1 |
| Apple | Vendor | Amd |
| Integrated | Build | Discrete |
| October 29, 2024 | Released | January 4, 2023 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | RDNA 3.0 |
| Custom | GPU Codename | Navi 33 |
| -Apple M4 (8-Core)or above | Recommended CPU | -AMD Ryzen 7 7735HSor above |
| 3450 | Steel Nomad Lite Score | 9302 |
| — | Time Spy | 10279 |
| 13908 | Solar Bay | 41160 |
| — | Port Royal | 5350 |
| — | Fire Strike | 28706 |
| 7928 | Wild Life Extreme | 17962 |
| — | Night Raid | 101381 |
| 500 MHz | Base Clock | 1500 MHz |
| 1470 MHz | Boost Clock | 1840-2200 MHz (configurable) |
| 1024 | Shading Units | 2048 |
| 64 | Texture Mapping Units (TMUs) | 128 |
| 32 | Render Output Units (ROPs) | 64 |
| 128 | Compute Units (Pipelines) | 32 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 32 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |