models · HuggingFaceTB
Small language model, 135M parameters. Designed for on-device and edge inference.
| Weight file SHA-256 | 0756756e5b0dfa1bb4d521dc96fc620010a1088d5aab87917cb5ff1c6a08476e |
|---|---|
| Method | self-download-sha256 |
| Publisher | HuggingFaceTB |
|---|---|
| Origin | United States |
| Licence | Apache-2.0 |
| Parameters | 134,515,008 (135M) |
| Architecture | llama |
| Layers | 30 |
| Hidden size | 576 |
| Attention | GQA (9 heads, 3 KV) |
| Native precision | F32 |
| Pulls recorded here | 7 |
| Downloads reported upstream | 172,818 |
Registry record as of 2026-09-26. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.