Community releases flood of Qwen3.8-27B fine-tunes and GGUF quantizations

How this story unfolded

3 weeks · 22 reports · 104 community posts · 126 of 135 shown

1. Aug 3
   • 4 community posts
2. Aug 4
   • More Qwen 3.8 sizes coming
3. Aug 11
   • Qwen 3.8-27b coming this week
4. Aug 12
   • Exact Qwen 3.8 27b release date and time
5. Aug 13
   • 4 community posts
6. Aug 14
   • 25 community posts
7. Aug 15
   • JonathanColetti/Qwen3.8-27B-Uncensored-GGUFhuggingface.co
   • orcarouter/Qwen3.8-27B-Uncensored-FP8huggingface.co
   • 5 community posts
8. Aug 16
   • Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUFhuggingface.co
   • AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16huggingface.co
   • empero-ai/Qwen3.8-27B-Ridge-GGUFhuggingface.co
   • 9 community posts
9. Aug 17
   • 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUFhuggingface.co
   • AtomicChat/Qwen3.8-27B-GGUFhuggingface.co
   • PocketAiHub/Qwen3.8-27B-Abliterated-MLXhuggingface.co
   • 21 community posts
10. 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
    • 12 community posts
11. Aug 19
    • DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUFhuggingface.co
    • z-lab/Qwen3.8-27B-DFlash2huggingface.co
    • bartowski/Qwen3.8-27B-GGUFhuggingface.co
    • 7 community posts
12. Aug 20
    • OBLITERATUS/Qwen3.8-27B-OBLITERATEDhuggingface.co
    • 10 community posts
13. Aug 21
    • EschaLabs/Qwen3.8-27B-Escha-W2huggingface.co
    • incoai/Qwen3.8-27B-DFlash2-GGUFhuggingface.co
14. Aug 22
    • Artificial Analysis "Intelligence": A meaningless benchmark
15. Aug 23
    • outsourc-e/Qwen3.8-27B-Unleashed-GGUFhuggingface.co
    • soyaakinohara/qwen3.8-27b-abliterated-3.69bpw-12GB-MTP.ggufhuggingface.co
    • z-lab/Qwen3.8-27B-DFlash2-GGUFhuggingface.co
    • orcarouter/Qwen3.8-27B-Uncensoredhuggingface.co
    • I gave Qwen 3.8 27B a reverse-engineering job I assumed needed a frontier model, and it finished in 30 minutes
16. Aug 24
    • This is what Qwen 3.8 27b is capable of
17. Aug 25
    • Top open models by use case 👇 chat - Kimi K3, Qwen3.8 2.4T A95B reasoning - Kimi K3, DeepSeek V4...