Qwen (Empero)
Family · 3 entries
Qwen (Empero), side by side
| Name | What to know | Price or memory | |
|---|---|---|---|
| Empero distilled the 2.4T-parameter Qwen teacher into a 4B student using ~45,000 curated reasoning traces; GGUF quants published | ~2.8 GB | ||
| Empero published Ridge, an architecture-aware 3.7 bpw GGUF of Qwen3.8-27B: 11.7 GB versus about 50 GB full size | ~14 GB | ||
| Community distillation of Qwen3.8 2.4T A95B into a 9B model, trained full-parameter on 70,000 teacher reasoning traces | ~44 GB | ||