Quick/Comparisons
9 | Gaming | 34 |
23 | Workstation | 41 |
12 | AI/ML |
Compare with something else?
Compare Apple M2 GPU with another →38 |
91 | Energy Efficiency | 47 |
27 | Quick Comparison Final Score | 37 |
| — | Graphics Processor | BMG-G21 |
| 1024 | Cores | 2560 |
| 64 / 32 | TMUs / ROPs | 160 / 80 |
| 301.33 | Blender GPU | 2106.04 |
| — | Forza Horizon 5 | 78 |
| — | The Witcher 3 | 128 |
| — | Counter-Strike 2 | 116 |
| — | Far Cry 6 | 98 |
| — | Hogwarts Legacy | 57 |
| — | Call of Duty | 85 |
| — | Ghost of Tsushima | 61 |
| — | Cyberpunk 2077 | 82 |
| — | Tomb Raider | 107 |
| — | Average FPS | 90 |
| — | 1080p High | 109 |
| — | 1080p Ultra | 90 |
| — | 1440p Ultra | 67 |
| — | 4K Ultra | 38 |
| — | Margin of Error | Low |
| 29705 | GB6 Compute Score | 111561 |
| 58.7 img/sec | Background Blur | 284.6 img/sec |
| 35.2 img/sec | Face Detection | 150 img/sec |
| 1.1 Gpixels/sec | Horizon Detection | 2.67 Gpixels/sec |
| 1.82 Gpixels/sec | Edge Detection | 5.22 Gpixels/sec |
| 1.2 Gpixels/sec | Gaussian Blur | 6.35 Gpixels/sec |
| 0.37 Gpixels/sec | Feature Matching | 1.18 Gpixels/sec |
| 96 Gpixels/sec | Stereo Matching | 397 Gpixels/sec |
| 3825.9 FPS | Particle Physics | 15177.3 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 15914 |
| — | G2D Mark | 700 |
| — | DirectX 11 | 126 FPS |
| — | DirectX 12 | 77 FPS |
| — | GPU Compute | 7896 Ops/s |
| 6206 | GB6 ML Single Precision | 21661 |
| 6893 | GB6 ML Half Precision | 34463 |
| 6515 | GB6 ML Quantized | 14366 |
| 3242 | Image Classification (SP) | 10654 |
| 4890 | Image Segmentation (HP) | 18608 |
| 7149 | Image Super Resolution (Q) | 16715 |
| 10340 | Face Detection (HP) | 40348 |
| 21268 | Pose Estimation (Q) | 64494 |
| 2268 | Text Classification (SP) | 3091 |
| 1122 | Machine Translation (HP) | 3530 |
| 3007 | Object Detection (SP) | 13690 |
| 13941 | Depth Estimation (Q) | 36797 |
| 35943 | Style Transfer (SP) | 197057 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 45 GPixel/s | Pixel Fill Rate | 214 GPixel/s |
| 89 GTexel/s | Texture Fill Rate | 427 GTexel/s |
| 2.9 TFLOPS | FLOPS (FP32) | 13.7 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 12 GB |
| 6400 MHz | Memory Clock | 2375 MHz |
| 12800 Mbps | Effective Memory Speed | 19000 Mbps |
| 128-bit | Bus | 192-bit |
| No | ECC | No |
| 102.4 GB/s | Memory Bandwidth | 456 GB/s |
| Custom | Interface | PCIe 4.0 x8 |
| 15 W | TGP | 190 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| — | Die Size | 272 mm² |
| 11.6 billion | Transistor Count | 19.6 billion |
| — | Transistor Density | 72.06 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | No |
| No | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1 |
| Apple | Vendor | Intel |
| Integrated | Build | Discrete |
| June 6, 2022 | Released | December 3, 2024 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Generation 12.7 |
| — | GPU Codename | BMG-G21 |
| -Apple M2or above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 2312 | Steel Nomad Lite Score | 11180 |
| — | Time Spy | 14665 |
| 7310 | Solar Bay | 55557 |
| — | Port Royal | 7919 |
| — | Fire Strike | 36685 |
| 5675 | Wild Life Extreme | 28324 |
| — | Night Raid | 123864 |
| 500 MHz | Base Clock | 1700 MHz |
| 1398 MHz | Boost Clock | 2670 MHz |
| 1024 | Shading Units | 2560 |
| 64 | Texture Mapping Units (TMUs) | 160 |
| 32 | Render Output Units (ROPs) | 80 |
| 128 | Compute Units (Pipelines) | 20 |
| — | Tensor Cores | 160 |
| — | Ray-tracing Cores | 20 |
| — | L1 Cache | 256KB per cluster |
| — | L2 Cache | 12MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |