@article{202407.1568, doi = {10.20944/preprints202407.1568.v1}, url = {https://doi.org/10.20944/preprints202407.1568.v1}, year = 2024, month = {July}, publisher = {Preprints}, author = {Bo Liu and Yuru Xu}, title = {Sparsity Limit to Prune Large Language Models for on-Device AI Assistants: Llama-2 as an Example}, journal = {Preprints} }