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 |
|---|---|---|
| .. | ||
| __init__.py 739 B | ||
| base.py 6.3 KB | ||
| hooks.py 3.7 KB | ||
| ling.py 17.7 KB | ||
| qwen.py 13.2 KB | ||