π“Ÿ host1.bitchan.one

𓀐 @CvZBiFH~

⏱ 5d seenβ›“ 0πŸ‘ 0β§– 1

filter [-]

languages:onother

Can anyone explain like im retarded the difference between all those gguf files on hugging face? https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/tree/main They range from 6 to 30 gigs. Are they all the same model? What are the difference between 1,2,3 bits etc, and q1, q2, q3, _K_XL and all that shit? I got a model working fine with ooga(qwen3.8 27B q2), im just trying to learn more but I don't seem to find any concrete info⏱ 4d↩ 4
It's the same model but compressed so less accurate, or rather it will make mistakes more often⏱ 5d↩
+ 3