# RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization

arXiv: https://arxiv.org/abs/2505.03803 · HTML: https://mlsanity.com/paper/2505.03803/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence](https://mlsanity.com/paper/2404.05892/) (2024)
- [Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures](https://mlsanity.com/paper/2403.02308/) (2024)
- [OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting](https://mlsanity.com/paper/2501.13987/) (2025)
- [QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension](https://mlsanity.com/paper/2107.12708/) (2021)
- [GPTVQ: The Blessing of Dimensionality for LLM Quantization](https://mlsanity.com/paper/2402.15319/) (2024)
- [VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2409.17066/) (2024)
- [A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset](https://mlsanity.com/paper/1806.00358/) (2018)
- [Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting](https://mlsanity.com/paper/2312.10588/) (2023)
- [A Survey of RWKV](https://mlsanity.com/paper/2412.14847/) (2024)
- [OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters](https://mlsanity.com/paper/2409.00286/) (2024)

## Built on by (most cited first, 4 of 4)

- [FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking](https://mlsanity.com/paper/2602.24133/) (2026)
- [TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization](https://mlsanity.com/paper/2605.19561/) (2026)
- [RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models](https://mlsanity.com/paper/2510.01240/) (2025)
- [Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models](https://mlsanity.com/paper/2605.19929/) (2026)

## Abstract (arXiv)

RWKV is a modern RNN architecture with comparable performance to Transformer, but still faces challenges when deployed to resource-constrained devices. Post Training Quantization (PTQ), which is a an essential technique to reduce model size and inference latency, has been widely used in Transformer models. However, it suffers significant degradation of performance when applied to RWKV. This paper investigates and identifies two key constraints inherent in the properties of RWKV: (1) Non-linear operators hinder the parameter-fusion of both smooth- and rotation-based quantization, introducing extra computation overhead. (2) The larger amount of uniformly distributed weights poses challenges for cluster-based quantization, leading to reduced accuracy. To this end, we propose RWKVQuant, a PTQ framework tailored for RWKV models, consisting of two novel techniques: (1) a coarse-to-fine proxy capable of adaptively selecting different quantization approaches by assessing the uniformity and identifying outliers in the weights, and (2) a codebook optimization algorithm that enhances the performance of cluster-based quantization methods for element-wise multiplication in RWKV. Experiments show that RWKVQuant can quantize RWKV-6-14B into about 3-bit with less than 1% accuracy loss and 2.14x speed up.