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 |
|---|---|---|
| .. | ||
| canonical.rs 1.0 KB | ||
| catalog.rs 7.5 KB | ||
| check.rs 6.9 KB | ||
| error.rs 790 B | ||
| fetch.rs 3.8 KB | ||
| lib.rs 284 B | ||
| mirror.rs 8.2 KB | ||
| registry_ops.rs 13.3 KB | ||
| runner.rs 29.9 KB | ||
| state_machine.rs 483 B | ||
| trust.rs 2.7 KB | ||