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 |
|---|---|---|
| .. | ||
| http | ||
| app.rs 13.7 KB | ||
| bus.rs 4.3 KB | ||
| http.rs 30.6 KB | ||
| lifecycle.rs 4.6 KB | ||
| main.rs 10.5 KB | ||
| registry.rs 5.0 KB | ||
| workers.rs 19.3 KB | ||