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 572 B | ||
| cache.py 2.4 KB | ||
| install.py 4.0 KB | ||
| layer.py 65.2 KB | ||
| mmap.py 3.8 KB | ||
| options.py 10.2 KB | ||