Quick/Comparisons
15 | Gaming | 45 |
25 | Workstation | 47 |
21 | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →44 |
95 | Energy Efficiency | 36 |
32 | Quick Comparison Final Score | 45 |
| Custom | Graphics Processor | Navi 21 |
| 1280 | Cores | 3840 |
| 80 / 40 | TMUs / ROPs | 240 / 96 |
| 1062.09 | Blender GPU | 1894.91 |
| — | Tomb Raider | 168 |
| — | Average FPS | 129 |
| — | Forza Horizon 5 | 116 |
| — | The Witcher 3 | 152 |
| — | Counter-Strike 2 | 186 |
| — | Far Cry 6 | 125 |
| — | Hogwarts Legacy | 88 |
| — | Call of Duty | 134 |
| — | Ghost of Tsushima | 90 |
| — | Cyberpunk 2077 | 98 |
| — | 1080p High | 157 |
| — | 1080p Ultra | 129 |
| — | 1440p Ultra | 95 |
| — | 4K Ultra | 55 |
| — | Margin of Error | Low |
| 37678 | GB6 Compute Score | 135060 |
| 72.2 img/sec | Background Blur | 298.6 img/sec |
| 48.3 img/sec | Face Detection | 186.2 img/sec |
| 1.4 Gpixels/sec | Horizon Detection | 4.75 Gpixels/sec |
| 1.94 Gpixels/sec | Edge Detection | 6.68 Gpixels/sec |
| 1.5 Gpixels/sec | Gaussian Blur | 5.58 Gpixels/sec |
| 0.53 Gpixels/sec | Feature Matching | 1.16 Gpixels/sec |
| 123.3 Gpixels/sec | Stereo Matching | 579 Gpixels/sec |
| 4938.4 FPS | Particle Physics | 18755.1 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 22023 |
| — | G2D Mark | 998 |
| — | DirectX 11 | 212 FPS |
| — | DirectX 12 | 89 FPS |
| — | GPU Compute | 10764 Ops/s |
| 10346 | GB6 ML Single Precision | 25097 |
| 11883 | GB6 ML Half Precision | 27988 |
| 11036 | GB6 ML Quantized | 19116 |
| 4874 | Image Classification (SP) | 11245 |
| 8168 | Image Segmentation (HP) | 13617 |
| 11983 | Image Super Resolution (Q) | 27747 |
| 17036 | Face Detection (HP) | 38124 |
| 31171 | Pose Estimation (Q) | 119493 |
| 2964 | Text Classification (SP) | 2425 |
| 3410 | Machine Translation (HP) | 5228 |
| 5112 | Object Detection (SP) | 11986 |
| 22700 | Depth Estimation (Q) | 46083 |
| 60872 | Style Transfer (SP) | 281860 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 59 GPixel/s | Pixel Fill Rate | 202 GPixel/s |
| 118 GTexel/s | Texture Fill Rate | 505 GTexel/s |
| 3.8 TFLOPS | FLOPS (FP32) | 16.2 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 16 GB |
| 7500 MHz | Memory Clock | 2000 MHz |
| 15000 Mbps | Effective Memory Speed | 16000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| 120 GB/s | Memory Bandwidth | 512 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 18 W | TGP | 250 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 7 nm |
| — | Die Size | 520 mm² |
| 28 billion | Transistor Count | 26 billion |
| — | Transistor Density | 50 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 |
| May 7, 2024 | Released | October 28, 2020 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | RDNA 2.0 |
| Custom | GPU Codename | Navi 21 |
| -Apple M4 (10-Core)or above | Recommended CPU | -Intel Core i5 12600or above |
| 4097 | Steel Nomad Lite Score | 14548 |
| — | Time Spy | 16220 |
| 16545 | Solar Bay | 64755 |
| — | Port Royal | 8137 |
| — | Fire Strike | 44377 |
| 9591 | Wild Life Extreme | 29764 |
| — | Night Raid | 142721 |
| 500 MHz | Base Clock | 1700 MHz |
| 1470 MHz | Boost Clock | 2105 MHz |
| 1280 | Shading Units | 3840 |
| 80 | Texture Mapping Units (TMUs) | 240 |
| 40 | Render Output Units (ROPs) | 96 |
| 160 | Compute Units (Pipelines) | — |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | 60 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |