Quick/Comparisons
14 | Gaming | 29 |
24 | Workstation | 35 |
| — | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →97 | Energy Efficiency | 46 |
32 | Quick Comparison Final Score | 33 |
| Custom | Graphics Processor | GA106 (GN20-E3) |
| 1024 | Cores | 3840 |
| 64 / 32 | TMUs / ROPs | 120 / 48 |
| 1060.26 | Blender GPU | 2342.93 |
| — | Forza Horizon 5 | 63 |
| — | The Witcher 3 | 93 |
| — | Counter-Strike 2 | 126 |
| — | Far Cry 6 | 82 |
| — | Hogwarts Legacy | 49 |
| — | Call of Duty | 68 |
| — | Ghost of Tsushima | 44 |
| — | Cyberpunk 2077 | 57 |
| — | Tomb Raider | 92 |
| — | Average FPS | 75 |
| — | 1080p High | 94 |
| — | 1080p Ultra | 75 |
| — | 1440p Ultra | 55 |
| — | 4K Ultra | 30 |
| — | Margin of Error | Low |
| 30791 | GB6 Compute Score | 94459 |
| 57.4 img/sec | Background Blur | 153.5 img/sec |
| 41.3 img/sec | Face Detection | 90 img/sec |
| 1.21 Gpixels/sec | Horizon Detection | 4.1 Gpixels/sec |
| 1.74 Gpixels/sec | Edge Detection | 5.77 Gpixels/sec |
| 1.12 Gpixels/sec | Gaussian Blur | 4.35 Gpixels/sec |
| 0.43 Gpixels/sec | Feature Matching | 1.01 Gpixels/sec |
| 94.9 Gpixels/sec | Stereo Matching | 385.9 Gpixels/sec |
| 3902.5 FPS | Particle Physics | 12770 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 13143 |
| — | G2D Mark | 585 |
| — | DirectX 11 | 109 FPS |
| — | DirectX 12 | 58 FPS |
| — | GPU Compute | 5649 Ops/s |
| — | GB6 ML Single Precision | 14362 |
| — | GB6 ML Half Precision | 25888 |
| — | GB6 ML Quantized | 9677 |
| — | Image Classification (SP) | 6257 |
| — | Image Segmentation (HP) | 16583 |
| — | Image Super Resolution (Q) | 12510 |
| — | Face Detection (HP) | 29528 |
| — | Pose Estimation (Q) | 51349 |
| — | Text Classification (SP) | 2685 |
| — | Machine Translation (HP) | 3939 |
| — | Object Detection (SP) | 7206 |
| — | Depth Estimation (Q) | 24343 |
| — | Style Transfer (SP) | 113151 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 47 GPixel/s | Pixel Fill Rate | 62-82 GPixel/s |
| 94 GTexel/s | Texture Fill Rate | 154-204 GTexel/s |
| 3 TFLOPS | FLOPS (FP32) | 9.9-13.1 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 6 GB |
| 7500 MHz | Memory Clock | 1750 MHz |
| 15000 Mbps | Effective Memory Speed | 12000-14000 Mbps |
| 128-bit | Bus | 192-bit |
| No | ECC | No |
| 120 GB/s | Memory Bandwidth | 336 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 15 W | TGP | 60-140 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 3 nm | Fabrication Process | 8 nm |
| — | Die Size | 300 mm² |
| — | Transistor Count | 13.25 billion |
| — | Transistor Density | 44.17 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2 |
| — | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 29, 2024 | Released | January 12, 2021 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Ampere |
| Custom | GPU Codename | GA106 (GN20-E3) |
| -Apple M4 (8-Core)or above | Recommended CPU | -Intel Core i5 12500Hor above |
| 3450 | Steel Nomad Lite Score | 8163 |
| — | Time Spy | 8319 |
| 13908 | Solar Bay | 36350 |
| — | Port Royal | 4709 |
| — | Fire Strike | 20179 |
| 7928 | Wild Life Extreme | 16476 |
| — | Night Raid | 72260 |
| 500 MHz | Base Clock | 816-1387 MHz (configurable) |
| 1470 MHz | Boost Clock | 1283-1703 MHz (configurable) |
| 1024 | Shading Units | 3840 |
| 64 | Texture Mapping Units (TMUs) | 120 |
| 32 | Render Output Units (ROPs) | 48 |
| 128 | Compute Units (Pipelines) | 30 |
| — | Tensor Cores | 120 |
| — | Ray-tracing Cores | 30 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 3MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |