AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models

Sangjun Lee, Seung-taek Woo, Jun-gyu Jin, Changhun Lee, Eunhyeok Park


Abstract
To enable broader deployment of Large Language Models (LLMs), it is essential to identify the best-performing model under strict memory constraints. We present AMQ, Automated Mixed-Precision Weight-Only Quantization, a framework that assigns layer-wise quantization bit-widths to optimally balance model quality and memory usage. However, the combinatorial search space, with over 10100 possible configurations, makes conventional black-box optimization infeasible. AMQ overcomes this challenge through four key innovations: (1) search space pruning using prior knowledge to exclude unpromising configurations, (2) quantization proxy to bypass costly format conversions during search, (3) quality predictor to minimize evaluation overhead, and (4) iterative search-and-update strategy for fast and stable convergence. By integrating these components, AMQ efficiently explores the quality–efficiency landscape, reaching the Pareto frontier and yielding LLMs that are both compact and high-performing.
Anthology ID:
2025.emnlp-main.1799
Volume:
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
35532–35550
Language:
URL:
https://aclanthology.org/2025.emnlp-main.1799/
DOI:
10.18653/v1/2025.emnlp-main.1799
Bibkey:
Cite (ACL):
Sangjun Lee, Seung-taek Woo, Jun-gyu Jin, Changhun Lee, and Eunhyeok Park. 2025. AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 35532–35550, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models (Lee et al., EMNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.emnlp-main.1799.pdf
Checklist:
 2025.emnlp-main.1799.checklist.pdf