Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments
For researchers in vector quantization, this work clarifies the relationship between two methods and highlights reproducibility concerns.
This note compares RaBitQ and TurboQuant under a unified framework, finding that TurboQuant does not consistently outperform RaBitQ and often performs worse; it also documents reproducibility issues in the TurboQuant paper.
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 does not provide a consistent improvement over RaBitQ in directly comparable settings; in many tested configurations, it performs worse than RaBitQ. 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.