Community Qwen3.8 fine-tunes and quants sweep Hugging Face
At least 15 community Qwen3.8 variants hit Hugging Face this week: abliterated/uncensored fine-tunes, GGUF quantizations, MLX conversions, and a 9B distill. Most-downloaded was empero-ai/Qwen3.8-9B-Distill-GGUF (71,582), ahead of huihui-ai's 27B abliterated GGUF (55,279), with the 9B Distill drawing the top trending score (130).
How this story unfolded
3 weeks · 23 reports · 103 community posts · 126 of 133 shown
- Aug 3
- Aug 11
- Aug 12
- Aug 13
- Aug 14
- Aug 15
- Aug 16
- Aug 17
- Aug 18
huihui-ai/Huihui-Qwen3.8-27B-abliteratedhuggingface.co
HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFhuggingface.co
orcarouter/Qwen3.8-27B-Uncensored-MLXhuggingface.co
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUFhuggingface.co
orcarouter/Qwen3.8-27B-Uncensored-GGUFhuggingface.co
empero-ai/Qwen3.8-9B-GGUFhuggingface.co
- Aug 19
- Aug 20
- Aug 21
Qwen by email
Get an email when Qwen has news
No news that day, no email.
More stories today
- Reduce RAG costs on Amazon Bedrock with query-aware compression
- AWS and Panasonic Avionics use agentic AI for aircraft IFEC diagnostics
- User's Claude memory system backfired; Claude said user was the bottleneck
- Claude users discuss when to choose Sonnet over Opus
- Building token-efficient multi-agent systems