# MobileQuant: Mobile-friendly Quantization for On-device Language Models

arXiv: https://arxiv.org/abs/2408.13933 · HTML: https://mlsanity.com/paper/2408.13933/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 25 Aug 2024.

## Builds on (most cited first, 17 of 17)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing](https://mlsanity.com/paper/2306.12929/) (2023)
- [FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization](https://mlsanity.com/paper/2306.00317/) (2023)

## Built on by (most cited first, 17 of 17)

- [MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization](https://mlsanity.com/paper/2502.00425/) (2025)
- [Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency](https://mlsanity.com/paper/2504.03360/) (2025)
- [Progressive Mixed-Precision Decoding for Efficient LLM Inference](https://mlsanity.com/paper/2410.13461/) (2024)
- [FPTQuant: Function-Preserving Transforms for LLM Quantization](https://mlsanity.com/paper/2506.04985/) (2025)
- [Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization](https://mlsanity.com/paper/2510.10618/) (2025)
- [Dissecting the Impact of Mobile DVFS Governors on LLM Inference Performance and Energy Efficiency](https://mlsanity.com/paper/2507.02135/) (2025)
- [FraQAT: Quantization Aware Training with Fractional bits](https://mlsanity.com/paper/2510.14823/) (2025)
- [EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation](https://mlsanity.com/paper/2605.04062/) (2026)
- [NOEM3A: a Neuro-symbolic Ontology-Enhanced Method for Multi-intent understanding in Mobile Agents](https://mlsanity.com/paper/2511.19780/) (2025)
- [S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations](https://mlsanity.com/paper/2602.14432/) (2026)
- [Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels](https://mlsanity.com/paper/2608.25053/) (2026)
- [Calibration and Transformation-Free Weight-Only LLMs Quantization via Dynamic Grouping](https://mlsanity.com/paper/2509.03054/) (2025)
- [HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices](https://mlsanity.com/paper/2605.05819/) (2026)
- [Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization](https://mlsanity.com/paper/2605.20295/) (2026)
- [Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment](https://mlsanity.com/paper/2608.15693/) (2026)
- [The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices](https://mlsanity.com/paper/2609.11940/) (2026)
- [ixi-sLM: On-Device sLM for AI Call Agent Service](https://mlsanity.com/paper/2610.19382/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have revolutionized language processing, delivering outstanding results across multiple applications. However, deploying LLMs on edge devices poses several challenges with respect to memory, energy, and compute costs, limiting their widespread use in devices such as mobile phones. A promising solution is to reduce the number of bits used to represent weights and activations. While existing works have found partial success at quantizing LLMs to lower bitwidths, e.g. 4-bit weights, quantizing activations beyond 16 bits often leads to large computational overheads due to poor on-device quantization support, or a considerable accuracy drop. Yet, 8-bit activations are very attractive for on-device deployment as they would enable LLMs to fully exploit mobile-friendly hardware, e.g. Neural Processing Units (NPUs). In this work, we make a first attempt to facilitate the on-device deployment of LLMs using integer-only quantization. We first investigate the limitations of existing quantization methods for on-device deployment, with a special focus on activation quantization. We then address these limitations by introducing a simple post-training quantization method, named MobileQuant, that extends previous weight equivalent transformation works by jointly optimizing the weight transformation and activation range parameters in an end-to-end manner. MobileQuant demonstrates superior capabilities over existing methods by 1) achieving near-lossless quantization on a wide range of LLM benchmarks, 2) reducing latency and energy consumption by 20%-50% compared to current on-device quantization strategies, 3) requiring limited compute budget, 4) being compatible with mobile-friendly compute units, e.g. NPU.