Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhan, Zaifu, Zhou, Shuang, Zeng, Min, Yu, Kai, Song, Meijia, Chen, Xiaoyi, Wang, Jun, Hou, Yu, Zhang, Rui
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911138780807168
author Zhan, Zaifu
Zhou, Shuang
Zeng, Min
Yu, Kai
Song, Meijia
Chen, Xiaoyi
Wang, Jun
Hou, Yu
Zhang, Rui
author_facet Zhan, Zaifu
Zhou, Shuang
Zeng, Min
Yu, Kai
Song, Meijia
Chen, Xiaoyi
Wang, Jun
Hou, Yu
Zhang, Rui
contents Large language models have demonstrated remarkable capabilities in biomedical natural language processing, yet their rapid growth in size and computational requirements present a major barrier to adoption in healthcare settings where data privacy precludes cloud deployment and resources are limited. In this study, we systematically evaluated the impact of quantization on 12 state-of-the-art large language models, including both general-purpose and biomedical-specific models, across eight benchmark datasets covering four key tasks: named entity recognition, relation extraction, multi-label classification, and question answering. We show that quantization substantially reduces GPU memory requirements-by up to 75%-while preserving model performance across diverse tasks, enabling the deployment of 70B-parameter models on 40GB consumer-grade GPUs. In addition, domain-specific knowledge and responsiveness to advanced prompting methods are largely maintained. These findings provide significant practical and guiding value, highlighting quantization as a practical and effective strategy for enabling the secure, local deployment of large yet high-capacity language models in biomedical contexts, bridging the gap between technical advances in AI and real-world clinical translation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04534
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation
Zhan, Zaifu
Zhou, Shuang
Zeng, Min
Yu, Kai
Song, Meijia
Chen, Xiaoyi
Wang, Jun
Hou, Yu
Zhang, Rui
Computation and Language
Artificial Intelligence
Large language models have demonstrated remarkable capabilities in biomedical natural language processing, yet their rapid growth in size and computational requirements present a major barrier to adoption in healthcare settings where data privacy precludes cloud deployment and resources are limited. In this study, we systematically evaluated the impact of quantization on 12 state-of-the-art large language models, including both general-purpose and biomedical-specific models, across eight benchmark datasets covering four key tasks: named entity recognition, relation extraction, multi-label classification, and question answering. We show that quantization substantially reduces GPU memory requirements-by up to 75%-while preserving model performance across diverse tasks, enabling the deployment of 70B-parameter models on 40GB consumer-grade GPUs. In addition, domain-specific knowledge and responsiveness to advanced prompting methods are largely maintained. These findings provide significant practical and guiding value, highlighting quantization as a practical and effective strategy for enabling the secure, local deployment of large yet high-capacity language models in biomedical contexts, bridging the gap between technical advances in AI and real-world clinical translation.
title Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.04534