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 |
|---|---|---|
| .. | ||
| chat.tsx 7.2 KB | ||
| models.tsx 12.7 KB | ||
| service.tsx 1.8 KB | ||
| settings.tsx 4.3 KB | ||
| status.tsx 7.7 KB | ||
| welcome.tsx 6.5 KB | ||