@article{spqrasparsequantizedrepresentationfor, title = {SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression}, author = {Tim Dettmers and Ruslan Svirschevski and Vage Egiazarian and Denis Kuznedelev and Elias Frantar and Saleh Ashkboos and Alexander Borzunov and Torsten Hoefler and Dan Alistarh}, year = {2023}, eprint = {2306.03078}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.03078v1}, }