SYLIN

Qwen (Empero)

Family · 3 entries

Qwen (Empero), side by side

NameWhat to knowPrice or memoryRanks
Qwen3.8-4B-DistillModelEmpero distilled the 2.4T-parameter Qwen teacher into a 4B student using ~45,000 curated reasoning traces; GGUF quants published~2.8 GB
Qwen3.8-27B RidgeModelEmpero published Ridge, an architecture-aware 3.7 bpw GGUF of Qwen3.8-27B: 11.7 GB versus about 50 GB full size~14 GB
Qwen3.8-9B (Empero)ModelCommunity distillation of Qwen3.8 2.4T A95B into a 9B model, trained full-parameter on 70,000 teacher reasoning traces~44 GB