Quick/Comparisons
19 | Gaming | 30 |
32 | Workstation | 34 |
34 | AI/ML |
Compare with something else?
Compare Apple M5 GPU with another →31 |
100 | Energy Efficiency | 39 |
38 | Quick Comparison Final Score | 31 |
| Custom | Graphics Processor | Navi 23 |
| 1280 | Cores | 2048 |
| 80 / 40 | TMUs / ROPs | 128 / 64 |
| 264.45 | Blender GPU | 1138.24 |
| — | Forza Horizon 5 | 76 |
| — | The Witcher 3 | 101 |
| — | Counter-Strike 2 | 130 |
| — | Far Cry 6 | 93 |
| — | Hogwarts Legacy | 59 |
| — | Call of Duty | 87 |
| — | Ghost of Tsushima | 63 |
| — | Cyberpunk 2077 | 65 |
| — | Tomb Raider | 111 |
| — | Average FPS | 87 |
| — | 1080p High | 112 |
| — | 1080p Ultra | 87 |
| — | 1440p Ultra | 61 |
| — | 4K Ultra | 32 |
| — | Margin of Error | Low |
| 75777 | GB6 Compute Score | 90831 |
| — | Background Blur | 220.1 img/sec |
| — | Face Detection | 128.3 img/sec |
| — | Horizon Detection | 2.94 Gpixels/sec |
| — | Edge Detection | 4.13 Gpixels/sec |
| — | Gaussian Blur | 3.68 Gpixels/sec |
| — | Feature Matching | 0.94 Gpixels/sec |
| — | Stereo Matching | 408.2 Gpixels/sec |
| — | Particle Physics | 10694.7 FPS |
| — | API | OpenCL |
| — | G3D Mark Score | 17117 |
| — | G2D Mark | 924 |
| — | DirectX 11 | 168 FPS |
| — | DirectX 12 | 62 FPS |
| — | GPU Compute | 7461 Ops/s |
| 13289 | GB6 ML Single Precision | 17945 |
| 24800 | GB6 ML Half Precision | 21242 |
| 23572 | GB6 ML Quantized | 13940 |
| 6348 | Image Classification (SP) | 8220 |
| 16813 | Image Segmentation (HP) | 9263 |
| 30322 | Image Super Resolution (Q) | 20723 |
| 34387 | Face Detection (HP) | 27074 |
| 111591 | Pose Estimation (Q) | 76541 |
| 2319 | Text Classification (SP) | 2796 |
| 5555 | Machine Translation (HP) | 4281 |
| 6450 | Object Detection (SP) | 6880 |
| 53195 | Depth Estimation (Q) | 33354 |
| 82314 | Style Transfer (SP) | 185358 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 65 GPixel/s | Pixel Fill Rate | 169 GPixel/s |
| 130 GTexel/s | Texture Fill Rate | 337 GTexel/s |
| 4.1 TFLOPS | FLOPS (FP32) | 10.8 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| 9600 MHz | Memory Clock | 2190 MHz |
| — | Effective Memory Speed | 17500 Mbps |
| 128-bit | Bus | 128-bit |
| No | ECC | No |
| 153 GB/s | Memory Bandwidth | 280.3 GB/s |
| Custom | Interface | PCIe 4.0 x8 |
| — | TGP | 176 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 7 nm |
| — | Die Size | 237 mm² |
| 28 billion | Transistor Count | 11 billion |
| — | Transistor Density | 46.41 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Amd |
| Integrated | Build | Discrete |
| October 15, 2025 | Released | May 10, 2022 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | RDNA 2.0 |
| Custom | GPU Codename | Navi 23 |
| -Apple M5 (10-Core)or above | Recommended CPU | -Intel Core i5 12600Kor above |
| 5337 | Steel Nomad Lite Score | 9265 |
| — | Time Spy | 9897 |
| 24534 | Solar Bay | 38892 |
| — | Port Royal | 4897 |
| — | Fire Strike | 29357 |
| 12266 | Wild Life Extreme | 18034 |
| — | Night Raid | 116256 |
| — | Base Clock | 2055 MHz |
| 1620 MHz | Boost Clock | 2635 MHz |
| 1280 | Shading Units | 2048 |
| 80 | Texture Mapping Units (TMUs) | 128 |
| 40 | Render Output Units (ROPs) | 64 |
| 160 | Compute Units (Pipelines) | — |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | 32 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |