# MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs

arXiv: https://arxiv.org/abs/2509.05488 · HTML: https://mlsanity.com/paper/2509.05488/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 11 of its 12 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Core SSM architectures for language](https://mlsanity.com/ssm/core-ssm-architectures-for-language/)

## Builds on (most cited first, 11 of 11)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://mlsanity.com/paper/2010.08678/) (2020)
- [Benchmarking TinyML Systems: Challenges and Direction](https://mlsanity.com/paper/2003.04821/) (2020)
- [Machine Learning for Microcontroller-Class Hardware: A Review](https://mlsanity.com/paper/2205.14550/) (2022)
- [Improving the Efficiency of Transformers for Resource-Constrained Devices](https://mlsanity.com/paper/2106.16006/) (2021)
- [Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices](https://mlsanity.com/paper/2412.09289/) (2024)

## Built on by (most cited first, 1 of 1)

- [BabyMamba-HAR: Lightweight Selective State Space Models for Efficient Human Activity Recognition on Resource Constrained Devices](https://mlsanity.com/paper/2602.09872/) (2026)

## Abstract (arXiv)

Deploying Mamba models on microcontrollers (MCUs) remains challenging due to limited memory, the lack of native operator support, and the absence of embedded-friendly toolchains. We present, to our knowledge, the first deployment of a Mamba-based neural architecture on a resource-constrained MCU, a fully C-based runtime-free inference engine: MambaLite-Micro. Our pipeline maps a trained PyTorch Mamba model to on-device execution by (1) exporting model weights into a lightweight format, and (2) implementing a handcrafted Mamba layer and supporting operators in C with operator fusion and memory layout optimization. MambaLite-Micro eliminates large intermediate tensors, reducing 83.0% peak memory, while maintaining an average numerical error of only 1.7x10-5 relative to the PyTorch Mamba implementation. When evaluated on keyword spotting(KWS) and human activity recognition (HAR) tasks, MambaLite-Micro achieved 100% consistency with the PyTorch baselines, fully preserving classification accuracy. We further validated portability by deploying on both ESP32S3 and STM32H7 microcontrollers, demonstrating consistent operation across heterogeneous embedded platforms and paving the way for bringing advanced sequence models like Mamba to real-world resource-constrained applications.