# Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization

arXiv: https://arxiv.org/abs/2501.16738 · HTML: https://mlsanity.com/paper/2501.16738/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 22 of its 23 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)

## Builds on (most cited first, 22 of 22)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [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)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization](https://mlsanity.com/paper/2111.12293/) (2021)
- [FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer](https://mlsanity.com/paper/2111.13824/) (2021)
- [EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba](https://mlsanity.com/paper/2403.09977/) (2024)
- [RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers](https://mlsanity.com/paper/2212.08254/) (2022)
- [EasyQuant: Post-training Quantization via Scale Optimization](https://mlsanity.com/paper/2006.16669/) (2020)
- [Quamba: A Post-Training Quantization Recipe for Selective State Space Models](https://mlsanity.com/paper/2410.13229/) (2024)
- [Mamba-PTQ: Outlier Channels in Recurrent Large Language Models](https://mlsanity.com/paper/2407.12397/) (2024)
- [MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2401.14895/) (2024)
- [TSPTQ-ViT: Two-scaled post-training quantization for vision transformer](https://mlsanity.com/paper/2305.12901/) (2023)

## 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)
- [Sequential Token Merging: Revisiting Hidden States](https://mlsanity.com/paper/2509.22691/) (2025)
- [ViM-Q: Scalable Algorithm-Hardware Co-Design for Vision Mamba Model Inference on FPGA](https://mlsanity.com/paper/2605.01935/) (2026)
- [Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality](https://mlsanity.com/paper/2609.16656/) (2026)

## Abstract (arXiv)

The Mamba model, utilizing a structured state-space model (SSM), offers linear time complexity and demonstrates significant potential. Vision Mamba (ViM) extends this framework to vision tasks by incorporating a bidirectional SSM and patch embedding, surpassing Transformer-based models in performance. While model quantization is essential for efficient computing, existing works have focused solely on the original Mamba model and have not been applied to ViM. Additionally, they neglect quantizing the SSM layer, which is central to Mamba and can lead to substantial error propagation by naive quantization due to its inherent structure. In this paper, we focus on the post-training quantization (PTQ) of ViM. We address the issues with three core techniques: 1) a k-scaled token-wise quantization method for linear and convolutional layers, 2) a reparameterization technique to simplify hidden state quantization, and 3) a factor-determining method that reduces computational overhead by integrating operations. Through these methods, the error caused by PTQ can be mitigated. Experimental results on ImageNet-1k demonstrate only a 0.8-1.2% accuracy degradation due to PTQ, highlighting the effectiveness of our approach.