@article{resqmixedprecisionquantizationoflarge,
  title = {ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals},
  author = {Utkarsh Saxena and Sayeh Sharify and Kaushik Roy and Xin Wang},
  year = {2024},
  eprint = {2412.14363},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.14363v1},
}