Quick/Comparisons
8 | Gaming | 9 |
21 | Workstation | 12 |
7 | AI/ML |
Compare with something else?
Compare Apple M1 GPU with another →13 |
89 | Energy Efficiency | 86 |
25 | Quick Comparison Final Score | 23 |
| — | Graphics Processor | Krackan Point |
| 1024 | Cores | 512 |
| 64 / 32 | TMUs / ROPs | 32 / 16 |
| 259.48 | Blender GPU | 193.82 |
| — | Forza Horizon 5 | 24 |
| — | The Witcher 3 | 18 |
| — | Counter-Strike 2 | 26 |
| — | Far Cry 6 | 26 |
| — | Hogwarts Legacy | 12 |
| — | Call of Duty | 27 |
| — | Ghost of Tsushima | 12 |
| — | Cyberpunk 2077 | 13 |
| — | Tomb Raider | 22 |
| — | Average FPS | 20 |
| — | 1080p High | 26 |
| — | 1080p Ultra | 20 |
| — | 1440p Ultra | 14 |
| — | 4K Ultra | - |
| — | Margin of Error | Low |
| 20842 | GB6 Compute Score | 22911 |
| 38.3 img/sec | Background Blur | 57.2 img/sec |
| 23 img/sec | Face Detection | 30.5 img/sec |
| 0.76 Gpixels/sec | Horizon Detection | 0.83 Gpixels/sec |
| 1.33 Gpixels/sec | Edge Detection | 1.16 Gpixels/sec |
| 0.87 Gpixels/sec | Gaussian Blur | 0.93 Gpixels/sec |
| 0.27 Gpixels/sec | Feature Matching | 0.35 Gpixels/sec |
| 69.9 Gpixels/sec | Stereo Matching | 97.8 Gpixels/sec |
| 2766.4 FPS | Particle Physics | 3933.5 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 4877 |
| — | G2D Mark | 916 |
| — | DirectX 11 | 37 FPS |
| — | DirectX 12 | 24 FPS |
| — | GPU Compute | 2421 Ops/s |
| 3284 | GB6 ML Single Precision | 6947 |
| 5418 | GB6 ML Half Precision | 10338 |
| 4395 | GB6 ML Quantized | 5334 |
| 1400 | Image Classification (SP) | 2022 |
| 2280 | Image Segmentation (HP) | 3987 |
| 3402 | Image Super Resolution (Q) | 6657 |
| 5638 | Face Detection (HP) | 10337 |
| 12027 | Pose Estimation (Q) | 28437 |
| 2324 | Text Classification (SP) | 2326 |
| 4296 | Machine Translation (HP) | 4011 |
| 1530 | Object Detection (SP) | 1995 |
| 7675 | Depth Estimation (Q) | 12031 |
| 17293 | Style Transfer (SP) | 56710 |
| Core ML | Framework | ONNX |
| CPU | Backend | DirectML |
| 41 GPixel/s | Pixel Fill Rate | 48 GPixel/s |
| 82 GTexel/s | Texture Fill Rate | 96 GTexel/s |
| 2.6 TFLOPS | FLOPS (FP32) | 3.1 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| 4266 MHz | Memory Clock | — |
| 8532 Mbps | Effective Memory Speed | — |
| 128-bit | Bus | — |
| No | ECC | — |
| 68.2 GB/s | Memory Bandwidth | — |
| Custom | Interface | PCIe 4.0 x16 |
| 15 W | TGP | 15-54 W (configurable) |
| Intel | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| — | Die Size | 233 mm² |
| 11.6 billion | Transistor Count | 34 billion |
| — | Transistor Density | 145.92 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.4 |
| — | OpenGL | 4.6 |
| — | OpenCL | 2.1 |
| — | CUDA | No |
| No | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1 |
| Apple | Vendor | Amd |
| Integrated | Build | Integrated |
| November 20, 2020 | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | RDNA 3.5 |
| — | GPU Codename | Krackan Point |
| -Apple M1or above | Recommended CPU | -AMD Ryzen AI 7 350or above |
| 1979 | Steel Nomad Lite Score | 2112 |
| — | Time Spy | 2565 |
| 6311 | Solar Bay | 11270 |
| — | Port Royal | 1103 |
| — | Fire Strike | 6835 |
| 4957 | Wild Life Extreme | 5150 |
| — | Night Raid | 29003 |
| 450 MHz | Base Clock | 600 MHz |
| 1278 MHz | Boost Clock | 3000 MHz |
| 1024 | Shading Units | 512 |
| 64 | Texture Mapping Units (TMUs) | 32 |
| 32 | Render Output Units (ROPs) | 16 |
| 128 | Compute Units (Pipelines) | 8 |
| — | Tensor Cores | No |
| No | Ray-tracing Cores | 8 |
| — | L1 Cache | 512KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |