Hi everyone! This is my attempt to benchmark and compare the quality of some of the well known Qwen3.6 27B quantizations on HuggingFace (unsloth, mradermacher, IQ4_XS from cHunter789 and Ununnilium), from Q8 all the way down to Q2. Measurement method I'm using llama.cpp's llama-perplexity to measure
