Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Python
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| cmake | ||
| mlx | ||
| .clang-format 2.5 KB | ||
| .gitignore 757 B | ||
| ACKNOWLEDGMENTS.md 14.2 KB | ||
| CMakeLists.txt 14.4 KB | ||
| LICENSE 1.0 KB | ||
| mlx.pc.in 1.7 KB | ||
| README.md 4.5 KB | ||