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 |
|---|---|---|
| .. | ||
| catalog.rs 1.6 KB | ||
| convert.rs 2.9 KB | ||
| doctor.rs 7.8 KB | ||
| engine.rs 11.4 KB | ||
| lib.rs 5.8 KB | ||
| main.rs 184 B | ||
| paths.rs 3.2 KB | ||
| pull.rs 14.2 KB | ||
| sink.rs 663 B | ||