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 |
|---|---|---|
| .. | ||
| _impl | ||
| __init__.py 305 B | ||
| backend.py 627 B | ||
| io.py 5.2 KB | ||
| quant.py 954 B | ||