4-bit quantization largely preserves LLM personality structure
Authors self-report: 4-bit quantization largely preserves coarse-grained personality structure, 2-bit breaks it
ImportanceLocalEvidenceE2 unreplicated
Model builders can now know that 4-bit quantization largely preserves the coarse-grained personality structure of large models, while 2-bit quantization breaks fine-grained prompt consistency and cross-precision consistency, and that personality decisions mainly form in the upper layers.
Previously, when choosing quantization for open-source large models, there was no layered MBTI personality analysis basis for whether personality structure changes with precision.
Yao Fu and five other authors performed a layered MBTI personality analysis on open-source large models, covering GPTQ, AWQ 4-bit and AQLM 2-bit quantization; the results are all self-reported by the authors.
The results have not been independently verified and serve only as a reference for quantization selection in personality-sensitive chat applications; preprint v2 was updated on September 15, first submitted on August 26, the page self-labels "in progress", arXiv:2608.25977.