deepseek-v4.1IMAGE
Local quant test: V4.1 Flash IQ2_XXS holds up against GLM-5.3-Flash in Maya
Testing local LLMs inside Maya, the author ranks DeepSeek-V4.1-Flash IQ2_XXS at least equal to GLM-5.3-Flash IQ2_XXS and above V4.1-Flash IQ1_S, and plans to use it in real work.
AuteDev
@autedev_comArchived 8 days agoOriginally posted 2026.10.23
AuteDev @autedev_comOriginally posted 2026.10.23
Mayaで動くLLMの品質を比較しました。 私の環境では DeepSeek-V4.1-Flash IQ2_XXS >= GLM-5.3-Flash IQ2_XXS ＞ DeepSeek-V4.1-Flash IQ1_S な感じですかね。今後実際に使っていきたいと思います。
x.com/autedev_com/status/2113478720447201358Archived 2026.10.24 12:08