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 |
|---|---|---|
| .. | ||
| e2e_smoke.py 3.3 KB | ||
| fetch_models.py 2.5 KB | ||
| generate_example.py 3.1 KB | ||
| strip_vision_weights.py 3.7 KB | ||
| upload_hf.py 4.2 KB | ||
| verify_alignment.py 6.1 KB | ||