Quick/Comparisons
15 | Gaming | 66 |
25 | Workstation | 79 |
21 | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →62 |
95 | Energy Efficiency | 49 |
32 | Quick Comparison Final Score | 66 |
| Custom | Graphics Processor | GB202-300-A1 |
| 1280 | Cores | 10496 |
| 80 / 40 | TMUs / ROPs | 328 / 112 |
| 1062.09 | Blender GPU | 7401.59 |
| — | Tomb Raider | 245 |
| — | Average FPS | 162 |
| — | Forza Horizon 5 | 135 |
| — | The Witcher 3 | 180 |
| — | Counter-Strike 2 | 214 |
| — | Far Cry 6 | 148 |
| — | Hogwarts Legacy | 114 |
| — | Call of Duty | 175 |
| — | Ghost of Tsushima | 106 |
| — | Cyberpunk 2077 | 145 |
| — | 1080p High | 191 |
| — | 1080p Ultra | 162 |
| — | 1440p Ultra | 127 |
| — | 4K Ultra | 75 |
| — | Margin of Error | High |
| 37678 | GB6 Compute Score | 246458 |
| 72.2 img/sec | Background Blur | 267.1 img/sec |
| 48.3 img/sec | Face Detection | 183.2 img/sec |
| 1.4 Gpixels/sec | Horizon Detection | 11.5 Gpixels/sec |
| 1.94 Gpixels/sec | Edge Detection | 15.8 Gpixels/sec |
| 1.5 Gpixels/sec | Gaussian Blur | 18.1 Gpixels/sec |
| 0.53 Gpixels/sec | Feature Matching | 2.01 Gpixels/sec |
| 123.3 Gpixels/sec | Stereo Matching | 1330 Gpixels/sec |
| 4938.4 FPS | Particle Physics | 35463.8 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 24043 |
| — | G2D Mark | 843 |
| — | DirectX 11 | 254 FPS |
| — | DirectX 12 | 109 FPS |
| — | GPU Compute | 8247 Ops/s |
| 10346 | GB6 ML Single Precision | 31330 |
| 11883 | GB6 ML Half Precision | 53746 |
| 11036 | GB6 ML Quantized | 24267 |
| 4874 | Image Classification (SP) | 12454 |
| 8168 | Image Segmentation (HP) | 33371 |
| 11983 | Image Super Resolution (Q) | 35476 |
| 17036 | Face Detection (HP) | 67998 |
| 31171 | Pose Estimation (Q) | 168369 |
| 2964 | Text Classification (SP) | 3491 |
| 3410 | Machine Translation (HP) | 6115 |
| 5112 | Object Detection (SP) | 16115 |
| 22700 | Depth Estimation (Q) | 59893 |
| 60872 | Style Transfer (SP) | 279891 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 59 GPixel/s | Pixel Fill Rate | 188-202 GPixel/s |
| 118 GTexel/s | Texture Fill Rate | 551-593 GTexel/s |
| 3.8 TFLOPS | FLOPS (FP32) | 35.3-37.9 TFLOPS |
| System Shared | Memory Type | GDDR7 |
| — | Memory Size | 24 GB |
| 7500 MHz | Memory Clock | 1750 MHz |
| 15000 Mbps | Effective Memory Speed | 28000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | — |
| 120 GB/s | Memory Bandwidth | 896 GB/s |
| Custom | Interface | PCIe 5.0 x16 |
| 18 W | TGP | 95-175 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | 378 mm² |
| 28 billion | Transistor Count | 45.6 billion |
| — | Transistor Density | 120.63 MTr/mm² |
| — | DirectX | 12.2 |
| — | Vulkan | 1.4 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 4 |
| — | DisplayPort | 2.1b |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| May 7, 2024 | Released | March 18, 2025 |
| Laptop | Case | Laptop |
| Professional | Purpose | Professional |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | Blackwell 2.0 |
| Custom | GPU Codename | GB202-300-A1 |
| -Apple M4 (10-Core)or above | Recommended CPU | -Intel Core Ultra 9 275HXor above |
| 4097 | Steel Nomad Lite Score | 24118 |
| — | Time Spy | 21548 |
| 16545 | Solar Bay | 96355 |
| — | Port Royal | 14090 |
| — | Fire Strike | 47636 |
| 9591 | Wild Life Extreme | — |
| — | Night Raid | — |
| 500 MHz | Base Clock | 990-1680 MHz (configurable) |
| 1470 MHz | Boost Clock | 1680-1807 MHz (configurable) |
| 1280 | Shading Units | 10496 |
| 80 | Texture Mapping Units (TMUs) | 328 |
| 40 | Render Output Units (ROPs) | 112 |
| 160 | Compute Units (Pipelines) | 82 |
| — | Tensor Cores | 328 |
| — | Ray-tracing Cores | 82 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |