Post #231818 2.13K Sep 8, 2026, 15:46 UTC Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapsesArticle, Comments Quesma Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses - Quesma Blog I test Unsloth GGUFs of Qwen3.8 27B (Q4_K_M, UD-Q2_K_XL, UD-IQ1_S) with llama.cpp on GPQA Diamond, IFBench, Terminal-Bench 2.1. Q4_K_M matches BF16 abd fits an RTX 4090. 👍 13 ❤ 5 🤮 1 🌭 1