ISTA-DASLab's IQ3_S quant is really good https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RC...
What are you running it on? I'm getting mixed results using the IQ3_XXS quant which supposedly matches baseline, it feels significantly degraded.
alt Hacker News
What are you running it on? I'm getting mixed results using the IQ3_XXS quant which supposedly matches baseline, it feels significantly degraded.