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 558 B | ||
| bailing_hybrid.py 36.4 KB | ||
| qwen3_5_moe.py 2.0 KB | ||
| qwen3_5.py 19.8 KB | ||
| qwen3_next.py 16.6 KB | ||