Quick/Comparisons
14 | Gaming | 9 |
24 | Workstation | 17 |
| — | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →97 | Energy Efficiency | 74 |
32 | Quick Comparison Final Score | 22 |
| Custom | Graphics Processor | TU117 |
| 1024 | Cores | 1024 |
| 64 / 32 | TMUs / ROPs | 32 / 16 |
| 1060.26 | Blender GPU | 240.21 |
| — | Forza Horizon 5 | 18 |
| — | The Witcher 3 | 22 |
| — | Counter-Strike 2 | 31 |
| — | Far Cry 6 | 28 |
| — | Hogwarts Legacy | 13 |
| — | Call of Duty | 27 |
| — | Ghost of Tsushima | 9 |
| — | Cyberpunk 2077 | 13 |
| — | Tomb Raider | 29 |
| — | Average FPS | 21 |
| — | 1080p High | 28 |
| — | 1080p Ultra | 21 |
| — | 1440p Ultra | 15 |
| — | 4K Ultra | - |
| — | Margin of Error | High |
| 30791 | GB6 Compute Score | 38596 |
| 57.4 img/sec | Background Blur | 70.9 img/sec |
| 41.3 img/sec | Face Detection | 37 img/sec |
| 1.21 Gpixels/sec | Horizon Detection | 1.28 Gpixels/sec |
| 1.74 Gpixels/sec | Edge Detection | 1.7 Gpixels/sec |
| 1.12 Gpixels/sec | Gaussian Blur | 1.9 Gpixels/sec |
| 0.43 Gpixels/sec | Feature Matching | 0.55 Gpixels/sec |
| 94.9 Gpixels/sec | Stereo Matching | 180.5 Gpixels/sec |
| 3902.5 FPS | Particle Physics | 5147.2 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 4443 |
| — | G2D Mark | 388 |
| — | DirectX 11 | 33 FPS |
| — | DirectX 12 | 28 FPS |
| — | GPU Compute | 2173 Ops/s |
| — | GB6 ML Single Precision | 4930 |
| — | GB6 ML Half Precision | 4630 |
| — | GB6 ML Quantized | 3611 |
| — | Image Classification (SP) | 1833 |
| — | Image Segmentation (HP) | 3301 |
| — | Image Super Resolution (Q) | 4390 |
| — | Face Detection (HP) | 5360 |
| — | Pose Estimation (Q) | 15739 |
| — | Text Classification (SP) | 1514 |
| — | Machine Translation (HP) | 1827 |
| — | Object Detection (SP) | 2338 |
| — | Depth Estimation (Q) | 8861 |
| — | Style Transfer (SP) | 37895 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 47 GPixel/s | Pixel Fill Rate | 21 GPixel/s |
| 94 GTexel/s | Texture Fill Rate | 42 GTexel/s |
| 3 TFLOPS | FLOPS (FP32) | 2.7 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 2 GB |
| 7500 MHz | Memory Clock | 1500 MHz |
| 15000 Mbps | Effective Memory Speed | 12000 Mbps |
| 128-bit | Bus | 64-bit |
| No | ECC | No |
| 120 GB/s | Memory Bandwidth | 96 GB/s |
| Custom | Interface | PCIe 4.0 x8 |
| 15 W | TGP | 25 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 12 nm |
| — | Die Size | 200 mm² |
| — | Transistor Count | 4.7 billion |
| — | Transistor Density | 23.5 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 7.5 |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | 1.4 |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 29, 2024 | Released | January 1, 2022 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Entry-level |
| Apple M GPU | Architecture | Turing |
| Custom | GPU Codename | TU117 |
| -Apple M4 (8-Core)or above | Recommended CPU | -Intel Core i7 1260Por above |
| 3450 | Steel Nomad Lite Score | 2514 |
| — | Time Spy | 2380 |
| 13908 | Solar Bay | — |
| — | Port Royal | — |
| — | Fire Strike | 5959 |
| 7928 | Wild Life Extreme | 5060 |
| — | Night Raid | 29231 |
| 500 MHz | Base Clock | 1065 MHz |
| 1470 MHz | Boost Clock | 1320 MHz |
| 1024 | Shading Units | 1024 |
| 64 | Texture Mapping Units (TMUs) | 32 |
| 32 | Render Output Units (ROPs) | 16 |
| 128 | Compute Units (Pipelines) | 8 |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | No |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |