@article{efficientdeploymentoflargelanguagemodels, title = {Efficient Deployment of Large Language Models on Resource-constrained Devices}, author = {Zhiwei Yao and Yang Xu and Hongli Xu and Yunming Liao and Zuan Xie}, year = {2025}, eprint = {2501.02438}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.02438v1}, }