Xingyu Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xingyu Zheng has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Jinyang Guo
Beihang University, Beijing, China
2 shared publications - Michele Magno
ETH Zurich
2 shared publications - Xianglong Liu
Beihang University, Beijing, China
2 shared publications - Chengtao Lv
Beihang University, Beijing, China
1 shared publication Dahua Lin
ETH Zurich, Rämistrasse 101, Zurich, 8092, Zurich, Switzerland; The Chinese University of Hong Kong, Shatin, NT, 999077, Hong Kong SAR, China
1 shared publicationHaoran Chu
Beihang University
1 shared publication
Latest Publications
- 15 July 2025
- Published by Elsevier in Neural Networks
- Vol. 192, 107856
A survey of low-bit large language models: Basics, systems, and algorithms
- 15 July 2025
- Published by Elsevier in Neural Networks
- Vol. 192, 107856
A survey of low-bit large language models: Basics, systems, and algorithms
- Open Access
An Empirical Study of Qwen3 Quantization
The Qwen series has emerged as a leading family of open-source Large Language Models (LLMs), demonstrating remarkable capabilities in natural language understanding tasks. With the recent release of Qwen3, which exhibits superior performance across diverse benchmarks, there is growing interest in deploying these models efficiently in resource-constrained environments. Low-bit quantization presents a promising solution, yet its impact on Qwen3's performance remains underexplored. This study conducts a systematic evaluation of Qwen3's robustness under various quantization settings, aiming to uncover both opportunities and challenges in compressing this state-of-the-art model. We rigorously assess 5 existing classic post-training quantization techniques applied to Qwen3, spanning bit-widths from 1 to 8 bits, and evaluate their effectiveness across multiple datasets. Our findings reveal that while Qwen3 maintains competitive performance at moderate bit-widths, it experiences notable degradation in linguistic tasks under ultra-low precision, underscoring the persistent hurdles in LLM compression. These results emphasize the need for further research to mitigate performance loss in extreme quantization scenarios. We anticipate that this empirical analysis will provide actionable insights for advancing quantization methods tailored to Qwen3 and future LLMs, ultimately enhancing their practicality without compromising accuracy. Our project is released on https://github.com/Efficient-ML/Qwen3-Quantization and https://huggingface.co/collections/Efficient-ML/qwen3-quantization-68164450decb1c868788cb2b.
Open AccessAn Empirical Study of Qwen3 Quantization
The Qwen series has emerged as a leading family of open-source Large Language Models (LLMs), demonstrating remarkable capabilities in natural language understanding tasks. With the recent release of Qwen3, which exhibits superior performance across diverse benchmarks, there is growing interest in deploying these models efficiently in resource-constrained environments. Low-bit quantization presents a promising solution, yet its impact on Qwen3's performance remains underexplored. This study conducts a systematic evaluation of Qwen3's robustness under various quantization settings, aiming to uncover both opportunities and challenges in compressing this state-of-the-art model. We rigorously assess 5 existing classic post-training quantization techniques applied to Qwen3, spanning bit-widths from 1 to 8 bits, and evaluate their effectiveness across multiple datasets. Our findings reveal that while Qwen3 maintains competitive performance at moderate bit-widths, it experiences notable degradation in linguistic tasks under ultra-low precision, underscoring the persistent hurdles in LLM compression. These results emphasize the need for further research to mitigate performance loss in extreme quantization scenarios. We anticipate that this empirical analysis will provide actionable insights for advancing quantization methods tailored to Qwen3 and future LLMs, ultimately enhancing their practicality without compromising accuracy. Our project is released on https://github.com/Efficient-ML/Qwen3-Quantization and https://huggingface.co/collections/Efficient-ML/qwen3-quantization-68164450decb1c868788cb2b.