# OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models

arXiv: https://arxiv.org/abs/2306.02272 · HTML: https://mlsanity.com/paper/2306.02272/

## Key facts

- Cited by 114 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 4 Jun 2023.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks](https://mlsanity.com/paper/1911.03852/) (2019)
- [QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization](https://mlsanity.com/paper/2203.05740/) (2022)
- [LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models](https://mlsanity.com/paper/2206.09557/) (2022)
- [Loss Aware Post-training Quantization](https://mlsanity.com/paper/1911.07190/) (2019)
- [Value-aware Quantization for Training and Inference of Neural Networks](https://mlsanity.com/paper/1804.07802/) (2018)

## Built on by (most cited first, 30 of 114)

- [A Survey on Model Compression for Large Language Models](https://mlsanity.com/paper/2308.07633/) (2023)
- [Efficient Large Language Models: A Survey](https://mlsanity.com/paper/2312.03863/) (2023)
- [A Survey of Resource-efficient LLM and Multimodal Foundation Models](https://mlsanity.com/paper/2401.08092/) (2024)
- [Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models](https://mlsanity.com/paper/2402.02244/) (2024)
- [PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression](https://mlsanity.com/paper/2405.14852/) (2024)
- [VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2409.17066/) (2024)
- [Optimizing Large Language Model Training Using FP4 Quantization](https://mlsanity.com/paper/2501.17116/) (2025)
- [Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs](https://mlsanity.com/paper/2402.10517/) (2024)
- [The Super Weight in Large Language Models](https://mlsanity.com/paper/2411.07191/) (2024)
- [CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2406.05223/) (2024)
- [Low-Rank Quantization-Aware Training for LLMs](https://mlsanity.com/paper/2406.06385/) (2024)
- [ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals](https://mlsanity.com/paper/2412.14363/) (2024)
- [STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs](https://mlsanity.com/paper/2408.01803/) (2024)
- [ARB-LLM: Alternating Refined Binarizations for Large Language Models](https://mlsanity.com/paper/2410.03129/) (2024)
- [MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization](https://mlsanity.com/paper/2411.05282/) (2024)
- [Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale](https://mlsanity.com/paper/2407.12327/) (2024)
- [Effective Interplay between Sparsity and Quantization: From Theory to Practice](https://mlsanity.com/paper/2405.20935/) (2024)
- [QSpec: Speculative Decoding with Complementary Quantization Schemes](https://mlsanity.com/paper/2410.11305/) (2024)
- [DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization](https://mlsanity.com/paper/2511.04063/) (2025)
- [ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference](https://mlsanity.com/paper/2511.10645/) (2025)
- [MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design](https://mlsanity.com/paper/2412.14590/) (2024)
- [Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression](https://mlsanity.com/paper/2505.19433/) (2025)
- [FPTQuant: Function-Preserving Transforms for LLM Quantization](https://mlsanity.com/paper/2506.04985/) (2025)
- [Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models](https://mlsanity.com/paper/2406.12311/) (2024)
- [Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization](https://mlsanity.com/paper/2503.18599/) (2025)
- [Post Training Quantization of Large Language Models with Microscaling Formats](https://mlsanity.com/paper/2405.07135/) (2024)
- [Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis](https://mlsanity.com/paper/2502.13178/) (2025)
- [Channel-Wise Mixed-Precision Quantization for Large Language Models](https://mlsanity.com/paper/2410.13056/) (2024)
- [Low-bit Model Quantization for Deep Neural Networks: A Survey](https://mlsanity.com/paper/2505.05530/) (2025)
- [MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models](https://mlsanity.com/paper/2508.02343/) (2025)

## Abstract (arXiv)

Large language models (LLMs) with hundreds of billions of parameters require powerful server-grade GPUs for inference, limiting their practical deployment. To address this challenge, we introduce the outlier-aware weight quantization (OWQ) method, which aims to minimize LLM's footprint through low-precision representation. OWQ prioritizes a small subset of structured weights sensitive to quantization, storing them in high-precision, while applying highly tuned quantization to the remaining dense weights. This sensitivity-aware mixed-precision scheme reduces the quantization error notably, and extensive experiments demonstrate that 3.1-bit models using OWQ perform comparably to 4-bit models optimized by OPTQ. Furthermore, OWQ incorporates a parameter-efficient fine-tuning for task-specific adaptation, called weak column tuning (WCT), enabling accurate task-specific LLM adaptation with minimal memory overhead in the optimized format. OWQ represents a notable advancement in the flexibility, efficiency, and practicality of LLM optimization literature. The source code is available at https://github.com/xvyaward/owq