Qwen3.8-27B sparks community GGUF releases and praise

How this story unfolded

4 weeks · 9 reports · 35 community posts · 44 of 49 shown

1. Aug 3
   • 2 community posts
2. Aug 12
   • Exact Qwen 3.8 27b release date and time
3. Aug 14
   • Qwen/Qwen3.8-27Bhuggingface.co
   • 6 community posts
4. Aug 15
   • 3 community posts
5. Aug 16
   • Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUFhuggingface.co
   • 2 community posts
6. Aug 17
   • 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUFhuggingface.co
   • AtomicChat/Qwen3.8-27B-GGUFhuggingface.co
   • DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1huggingface.co
   • 4 community posts
7. Aug 18
   • orcarouter/Qwen3.8-27B-Uncensored-MLXhuggingface.co
   • Qwen 3.8 27b saved me $650+ in API costs this evening
8. Aug 19
   • Qwen3.8-27B is live on Tinker today. It’s natively multimodal with images + video, has flexible...
9. Aug 20
   • 3 community posts
10. Aug 21
    • 2 community posts
11. Aug 23
    • outsourc-e/Qwen3.8-27B-Unleashed-GGUFhuggingface.co
    • Tested in Coding: Q8_K_XL Qwen3.8 27B vs BF16 Qwen3.6 27B
12. Aug 24
    • This Small AI Will Change Everythingyoutube.com
    • Qwen 3.8 27B in 9th position on code arena. Gemma 4 31B is 80th.
13. Aug 26
    • Fully quantized NVFP4 Qwen3.8-27B with QUASAR QAD
14. Aug 27
    • Over 200k context on 16GB VRAM with Qwen 3.8 27B UD-IQ3_XXS
15. Aug 28
    • Run Qwen3.8 27B locally: real numbers from my Mac Studio
16. Aug 31
    • ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUFhuggingface.co
    • 2 community posts
17. Sep 1
    • 2 community posts
18. Sep 2
    • Everyone is t/s maxing.. 3.8.. but after a week of using it for work I'm tempted to switch back to 3.6