Preprint
Aug 2026
Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization
ScaleQ-1.58 is proposed, a scalable ternary post-training quantization (PTQ) framework for reasoning LLMs that demonstrates strong generalization across tasks of varying difficulty levels, including mathematics, coding and scientific logic reasoning, as well as commonsense reasoning and basic language generation.
Shi-Geng Wang, Chao Li, Yangyuxuan Kang et al.
· 3 citations