Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments

Jianyang Gao; Yutong Gou; Yuexuan Xu; Jifan Shi; Yongyi Yang; Shuolin Li; Raymond Chi-Wing Wong; Cheng Long

cs.LGApr 21, 2026

Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments

Authors: Jianyang Gao, Yutong Gou, Yuexuan Xu, Jifan Shi, Yongyi Yang, Shuolin Li, Raymond Chi-Wing Wong, Cheng Long

Organizations: ETH Zurich · Nanyang Technological University · University of Michigan · Tsinghua University · HKUST

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.

Explore similar work

A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work
Apr 20, 2026Ran Ben-Basat, Yaniv Ben-Itzhak, Gal Mendelson +3Quantizer Drives
Ablation, Statistical Inference, and Validation for KV-Cache Compression
Jun 14, 2026Paolo D'Alberto, Ashish Siarasao, Elliott Delaye +1Key-Value Cache Compression Calibration-Free Low-Bit Vector Quantization
TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization
Jul 18, 2026Navnit Shukla, Kamal Pandey, Omsankar TiwariVector Database Retrieval Recall

Apr 20, 2026 · cs.LGJ/K move · Enter open · S save

A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work

Ran Ben-Basat, Yaniv Ben-Itzhak, Gal Mendelson, Michael Mitzenmacher+2

UCL and Broadcom · VMware Research by Broadcom · North Carolina State University · Harvard University · Microsoft

This note clarifies the relationship between the recent TurboQuant work and the earlier DRIVE (NeurIPS 2021) and EDEN (ICML 2022) schemes. DRIVE is a 1-bit quantizer that EDEN extended to any

b>0

bits per coordinate; we refer to them collectively as EDEN. First, TurboQuant

_{\text{mse}}

is a special case of EDEN obtained by fixing EDEN's scalar scale parameter to

S=1

. EDEN supports both biased and unbiased quantization, each optimized by a different

S

(chosen via methods described in the EDEN works). The fixed choice

S=1

used by TurboQuant is generally suboptimal, although the optimal

S

for biased EDEN converges to

1

as the dimension grows; accordingly TurboQuant

_{\text{mse}}

approaches EDEN's behavior for large

d

. Second, TurboQuant

_{\text{prod}}

combines a biased

(b-1)

-bit EDEN step with an unbiased 1-bit QJL quantization of the residual. It is suboptimal in three ways: (1) its

(b-1)

-bit step uses the suboptimal

S=1

; (2) its 1-bit unbiased residual quantization has worse MSE than (unbiased) 1-bit EDEN; (3) chaining a biased

(b-1)

-bit step with a 1-bit unbiased residual step is inferior to unbiasedly quantizing the input directly with

b

-bit EDEN. Third, some of the analysis in the TurboQuant work mirrors that of the EDEN works: both exploit the connection between random rotations and the shifted Beta distribution, use the Lloyd-Max algorithm, and note that Randomized Hadamard Transforms can replace uniform random rotations. Experiments support these claims: biased EDEN (with optimized

S

) is more accurate than TurboQuant

_{\text{mse}}

, and unbiased EDEN is markedly more accurate than TurboQuant

_{\text{prod}}

, often by more than a bit (e.g., 2-bit EDEN beats 3-bit TurboQuant

_{\text{prod}}

). We also repeat all accuracy experiments from the TurboQuant paper, showing that EDEN outperforms it in every setup we have tried.

Quantizer Drives

Open paper Ask about it PDF

Abstract

Explore similar work

A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work

Ablation, Statistical Inference, and Validation for KV-Cache Compression

TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization