Quick/Comparisons
15 | Gaming | 61 |
25 | Workstation | 69 |
21 | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →53 |
95 | Energy Efficiency | 35 |
32 | Quick Comparison Final Score | 62 |
| Custom | Graphics Processor | GA102 |
| 1280 | Cores | 10496 |
| 80 / 40 | TMUs / ROPs | 328 / 112 |
| 1062.09 | Blender GPU | 5800.59 |
| — | Tomb Raider | 226 |
| — | Average FPS | 153 |
| — | Forza Horizon 5 | 125 |
| — | The Witcher 3 | 175 |
| — | Counter-Strike 2 | 212 |
| — | Far Cry 6 | 142 |
| — | Hogwarts Legacy | 106 |
| — | Call of Duty | 159 |
| — | Ghost of Tsushima | 97 |
| — | Cyberpunk 2077 | 132 |
| — | 1080p High | 179 |
| — | 1080p Ultra | 153 |
| — | 1440p Ultra | 119 |
| — | 4K Ultra | 70 |
| — | Margin of Error | Low |
| 37678 | GB6 Compute Score | 211669 |
| 72.2 img/sec | Background Blur | 320.8 img/sec |
| 48.3 img/sec | Face Detection | 207.2 img/sec |
| 1.4 Gpixels/sec | Horizon Detection | 10.1 Gpixels/sec |
| 1.94 Gpixels/sec | Edge Detection | 14.4 Gpixels/sec |
| 1.5 Gpixels/sec | Gaussian Blur | 11.5 Gpixels/sec |
| 0.53 Gpixels/sec | Feature Matching | 1.48 Gpixels/sec |
| 123.3 Gpixels/sec | Stereo Matching | 984.2 Gpixels/sec |
| 4938.4 FPS | Particle Physics | 27764.9 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 26551 |
| — | G2D Mark | 1069 |
| — | DirectX 11 | 218 FPS |
| — | DirectX 12 | 110 FPS |
| — | GPU Compute | 15117 Ops/s |
| 10346 | GB6 ML Single Precision | 27237 |
| 11883 | GB6 ML Half Precision | 41500 |
| 11036 | GB6 ML Quantized | 15927 |
| 4874 | Image Classification (SP) | 10665 |
| 8168 | Image Segmentation (HP) | 28963 |
| 11983 | Image Super Resolution (Q) | 22697 |
| 17036 | Face Detection (HP) | 55232 |
| 31171 | Pose Estimation (Q) | 128155 |
| 2964 | Text Classification (SP) | 3152 |
| 3410 | Machine Translation (HP) | 5088 |
| 5112 | Object Detection (SP) | 13891 |
| 22700 | Depth Estimation (Q) | 37984 |
| 60872 | Style Transfer (SP) | 272000 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 59 GPixel/s | Pixel Fill Rate | 190 GPixel/s |
| 118 GTexel/s | Texture Fill Rate | 556 GTexel/s |
| 3.8 TFLOPS | FLOPS (FP32) | 35.6 TFLOPS |
| System Shared | Memory Type | GDDR6X |
| — | Memory Size | 24 GB |
| 7500 MHz | Memory Clock | 1219 MHz |
| 15000 Mbps | Effective Memory Speed | 19500 Mbps |
| 128-bit | Bus | 384-bit |
| No | ECC | No |
| 120 GB/s | Memory Bandwidth | 936.2 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 18 W | TGP | 350 W |
| TSMC | Manufacturing | Samsung |
| 3 nm | Fabrication Process | 8 nm |
| — | Die Size | 628 mm² |
| 28 billion | Transistor Count | 28 billion |
| — | Transistor Density | 44.59 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| May 7, 2024 | Released | September 24, 2020 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | Ampere |
| Custom | GPU Codename | GA102 |
| -Apple M4 (10-Core)or above | Recommended CPU | -Intel Core i9 12900Kor above |
| 4097 | Steel Nomad Lite Score | 21851 |
| — | Time Spy | 19896 |
| 16545 | Solar Bay | 97375 |
| — | Port Royal | 13631 |
| — | Fire Strike | 47515 |
| 9591 | Wild Life Extreme | 43673 |
| — | Night Raid | 139755 |
| 500 MHz | Base Clock | 1395 MHz |
| 1470 MHz | Boost Clock | 1695 MHz |
| 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 | 6MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |