architectures · qwen
Qwen3 adds a hybrid thinking mode toggle: standard fast decoding or extended reasoning with think tokens. Uses GQA, RoPE, and SwiGLU throughout.
| Weight file SHA-256 | bdb2545734738da2dcd1b68c0ae9a896b4823206efe129fb48500eefe53dbd35 |
|---|
| Publisher | qwen |
|---|---|
| Origin | China |
| Licence | Apache-2.0 |
| Modality | Text |
| Pulls recorded here | 52,001 |
Registry record as of 2026-08-14. 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.