@article{sherryhardwareefficient125bitternaryquan, title = {Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification}, author = {Hong Huang and Decheng Wu and Qiangqiang Hu and Guanghua Yu and Jinhai Yang and Jianchen Zhu and Xue Liu and Dapeng Wu}, year = {2026}, eprint = {2601.07892}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.07892}, }