# QMamba: Post-Training Quantization for Vision State Space Models

arXiv: https://arxiv.org/abs/2501.13624 · HTML: https://mlsanity.com/paper/2501.13624/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2025.

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

- [OuroMamba: A Data-Free Quantization Framework for Vision Mamba](https://mlsanity.com/paper/2503.10959/) (2025)
- [Quantizing Small-Scale State-Space Models for Edge AI](https://mlsanity.com/paper/2506.12480/) (2025)
- [Quantizing Looped Transformers: Feedback Exposure and Calibration Blindness](https://mlsanity.com/paper/2609.30820/) (2026)
- [Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality](https://mlsanity.com/paper/2609.16656/) (2026)

## Abstract (arXiv)

State Space Models (SSMs), as key components of Mamaba, have gained increasing attention for vision models recently, thanks to their efficient long sequence modeling capability. Given the computational cost of deploying SSMs on resource-limited edge devices, Post-Training Quantization (PTQ) is a technique with the potential for efficient deployment of SSMs. In this work, we propose QMamba, one of the first PTQ frameworks to our knowledge, designed for vision SSMs based on the analysis of the activation distributions in SSMs. We reveal that the distribution of discrete parameters exhibits long-tailed skewness and the distribution of the hidden state sequence exhibits highly dynamic variations. Correspondingly, we design Long-tailed Skewness Quantization (LtSQ) to quantize discrete parameters and Temporal Group Quantization (TGQ) to quantize hidden states, which reduces the quantization errors. Extensive experiments demonstrate that QMamba outperforms advanced PTQ methods on vision models across multiple model sizes and architectures. Notably, QMamba surpasses existing methods by 21.0% on ImageNet classification with 4-bit activations.