Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments
Abstract
This technical note revisits the relationship between RaBitQ and TurboQuant under a unified comparison framework. We compare the two methods in terms of methodology, theoretical guarantees, and empirical performance, using a reproducible, transparent, and symmetric setup. Our results show that, despite the claimed advantage of TurboQuant, TurboQuant performs worse than RaBitQ in most tested settings of inner-product estimation, nearest-neighbor search and KV cache quantization. We further find that several reported runtime and recall results in the TurboQuant paper could not be reproduced from the released implementation under the stated configuration. Overall, this note clarifies the shared structure and genuine differences between the two lines of work, while documenting reproducibility issues in the experimental results reported by the TurboQuant paper.
Keywords
Cite
@article{arxiv.2604.19528,
title = {Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments},
author = {Jianyang Gao and Yutong Gou and Yuexuan Xu and Jifan Shi and Yongyi Yang and Shuolin Li and Raymond Chi-Wing Wong and Cheng Long},
journal= {arXiv preprint arXiv:2604.19528},
year = {2026}
}