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 |
|---|---|---|
| .. | ||
| README.md 3.9 KB | ||
| results.csv 317 B | ||
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
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| README.md 3.9 KB | ||
| results.csv 317 B | ||