DeepSeek V4.1 Flash 1017 full weights tie IQ2_XS quant on 367 tasks, full model slightly worse

unbug @unbugOriginally posted 2026.10.24

Open original on X

WTF! I had official DeepSeek V4.1 Flash 1017 run a full eval of @mhelcig’s local GSQ-RCO IQ2_XS to measure the gap vs. the full-weight model. 1.5 hours and 367 tasks later, both passed everything—and the full-weight version actually scored a hair worse than IQ2_XS. Even the full model won’t accept that result.😅

This post quotes another post: x.com/unbug/status/2113882538267853216