Quick/Comparisons
14 | Gaming | 14 |
24 | Workstation | 23 |
| — | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →97 | Energy Efficiency | 50 |
32 | Quick Comparison Final Score | 18 |
| Custom | Graphics Processor | Navi 14 |
| 1024 | Cores | 1408 |
| 64 / 32 | TMUs / ROPs | 88 / 32 |
| 1060.26 | Blender GPU | 504 |
| — | Forza Horizon 5 | 45 |
| — | The Witcher 3 | 46 |
| — | Counter-Strike 2 | 64 |
| — | Far Cry 6 | 49 |
| — | Hogwarts Legacy | 29 |
| — | Call of Duty | 43 |
| — | Ghost of Tsushima | 27 |
| — | Cyberpunk 2077 | 29 |
| — | Tomb Raider | 58 |
| — | Average FPS | 43 |
| — | 1080p High | 57 |
| — | 1080p Ultra | 43 |
| — | 1440p Ultra | 28 |
| — | 4K Ultra | 14 |
| — | Margin of Error | Low |
| 30791 | GB6 Compute Score | 43831 |
| 57.4 img/sec | Background Blur | 93.3 img/sec |
| 41.3 img/sec | Face Detection | 48.3 img/sec |
| 1.21 Gpixels/sec | Horizon Detection | 1.68 Gpixels/sec |
| 1.74 Gpixels/sec | Edge Detection | 2.43 Gpixels/sec |
| 1.12 Gpixels/sec | Gaussian Blur | 1.99 Gpixels/sec |
| 0.43 Gpixels/sec | Feature Matching | 0.48 Gpixels/sec |
| 94.9 Gpixels/sec | Stereo Matching | 144.1 Gpixels/sec |
| 3902.5 FPS | Particle Physics | 5990 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 9068 |
| — | G2D Mark | 778 |
| — | DirectX 11 | 55 FPS |
| — | DirectX 12 | 40 FPS |
| — | GPU Compute | 4362 Ops/s |
| — | GB6 ML Single Precision | 9492 |
| — | GB6 ML Half Precision | 11381 |
| — | GB6 ML Quantized | 7407 |
| — | Image Classification (SP) | 3640 |
| — | Image Segmentation (HP) | 4585 |
| — | Image Super Resolution (Q) | 11173 |
| — | Face Detection (HP) | 12599 |
| — | Pose Estimation (Q) | 39745 |
| — | Text Classification (SP) | 1739 |
| — | Machine Translation (HP) | 3457 |
| — | Object Detection (SP) | 3801 |
| — | Depth Estimation (Q) | 18563 |
| — | Style Transfer (SP) | 83214 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 47 GPixel/s | Pixel Fill Rate | 59 GPixel/s |
| 94 GTexel/s | Texture Fill Rate | 162 GTexel/s |
| 3 TFLOPS | FLOPS (FP32) | 5.2 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 4 GB |
| 7500 MHz | Memory Clock | 1750 MHz |
| 15000 Mbps | Effective Memory Speed | 14000 Mbps |
| 128-bit | Bus | 128-bit |
| No | ECC | No |
| 120 GB/s | Memory Bandwidth | 224 GB/s |
| Custom | Interface | PCIe 4.0 x8 |
| 15 W | TGP | 130 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 7 nm |
| — | Die Size | 158 mm² |
| — | Transistor Count | 6 billion |
| — | Transistor Density | 37.97 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Amd |
| Integrated | Build | Discrete |
| October 29, 2024 | Released | December 12, 2019 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | RDNA 1.0 |
| Custom | GPU Codename | Navi 14 |
| -Apple M4 (8-Core)or above | Recommended CPU | -Intel Core i5 9400or above |
| 3450 | Steel Nomad Lite Score | 4420 |
| — | Time Spy | 4853 |
| 13908 | Solar Bay | — |
| — | Port Royal | — |
| — | Fire Strike | 14381 |
| 7928 | Wild Life Extreme | 9511 |
| — | Night Raid | 60098 |
| 500 MHz | Base Clock | 1607 MHz |
| 1470 MHz | Boost Clock | 1845 MHz |
| 1024 | Shading Units | 1408 |
| 64 | Texture Mapping Units (TMUs) | 88 |
| 32 | Render Output Units (ROPs) | 32 |
| 128 | Compute Units (Pipelines) | — |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | No |
| — | L1 Cache | — |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |