Qwen3.8-27B open-weight model sparks community fine-tunes

How this story unfolded

3 weeks · 11 reports · 44 community posts · 55 of 61 shown

1. Aug 3
   • 2 community posts
2. Aug 13
   • The countdown to Qwen3.8-27B starts now!
3. Aug 14
   • 11 community posts
4. Aug 15
   • JonathanColetti/Qwen3.8-27B-Uncensored-GGUFhuggingface.co
   • orcarouter/Qwen3.8-27B-Uncensored-FP8huggingface.co
   • simple: llama serve -hf ggml-org/Qwen3.8-27B-GGUF --spec-type draft-mtp
5. Aug 16
   • empero-ai/Qwen3.8-27B-Ridge-GGUFhuggingface.co
   • 3 community posts
6. Aug 17
   • 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUFhuggingface.co
   • 7 community posts
7. Aug 18
   • orcarouter/Qwen3.8-27B-Uncensored-MLXhuggingface.co
   • 5 community posts
8. Aug 19
   • z-lab/Qwen3.8-27B-DFlash2huggingface.co
   • bartowski/Qwen3.8-27B-GGUFhuggingface.co
   • 2 community posts
9. Aug 20
   • 4 community posts
10. Aug 21
    • 2 community posts
11. Aug 23
    • soyaakinohara/qwen3.8-27b-abliterated-3.69bpw-12GB-MTP.ggufhuggingface.co
    • orcarouter/Qwen3.8-27B-Uncensoredhuggingface.co
    • We quantized Qwen 3.8 27B and compared the quants on an RTX 6000
12. Aug 24
    • Qwen 3.8 27B Aider score
13. Aug 26
    • Alibaba Releases Smaller, Cost-Effective Qwen AI Modelbloomberg.com
    • How To EASILY Run Local AI Modelsyoutube.com
    • 4 community posts