# FracBits: Mixed Precision Quantization via Fractional Bit-Widths

arXiv: https://arxiv.org/abs/2007.02017 · HTML: https://mlsanity.com/paper/2007.02017/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2020.

## Built on by (most cited first, 30 of 55)

- [IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization](https://mlsanity.com/paper/2111.09136/) (2021)
- [OMPQ: Orthogonal Mixed Precision Quantization](https://mlsanity.com/paper/2109.07865/) (2021)
- [Teachers Do More Than Teach: Compressing Image-to-Image Models](https://mlsanity.com/paper/2103.03467/) (2021)
- [Q-ViT: Fully Differentiable Quantization for Vision Transformer](https://mlsanity.com/paper/2201.07703/) (2022)
- [F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization](https://mlsanity.com/paper/2202.05239/) (2022)
- [SDQ: Stochastic Differentiable Quantization with Mixed Precision](https://mlsanity.com/paper/2206.04459/) (2022)
- [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://mlsanity.com/paper/2207.10345/) (2022)
- [A Practical Mixed Precision Algorithm for Post-Training Quantization](https://mlsanity.com/paper/2302.05397/) (2023)
- [EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization](https://mlsanity.com/paper/2307.10554/) (2023)
- [CPT: Efficient Deep Neural Network Training via Cyclic Precision](https://mlsanity.com/paper/2101.09868/) (2021)
- [Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning](https://mlsanity.com/paper/2302.04453/) (2023)
- [Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision](https://mlsanity.com/paper/2307.00331/) (2023)
- [Retraining-free Model Quantization via One-Shot Weight-Coupling Learning](https://mlsanity.com/paper/2401.01543/) (2024)
- [Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices](https://mlsanity.com/paper/2311.18129/) (2023)
- [Low-bit Model Quantization for Deep Neural Networks: A Survey](https://mlsanity.com/paper/2505.05530/) (2025)
- [Confounding Tradeoffs for Neural Network Quantization](https://mlsanity.com/paper/2102.06366/) (2021)
- [RefQSR: Reference-based Quantization for Image Super-Resolution Networks](https://mlsanity.com/paper/2404.01690/) (2024)
- [MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization](https://mlsanity.com/paper/2311.06798/) (2023)
- [Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization](https://mlsanity.com/paper/2410.19483/) (2024)
- [SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization](https://mlsanity.com/paper/2302.06845/) (2023)
- [MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization](https://mlsanity.com/paper/2305.08117/) (2023)
- [Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks](https://mlsanity.com/paper/2407.01054/) (2024)
- [Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks](https://mlsanity.com/paper/2307.13337/) (2023)
- [CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians](https://mlsanity.com/paper/2505.21041/) (2025)
- [Sharpness-Aware Data Generation for Zero-shot Quantization](https://mlsanity.com/paper/2510.07018/) (2025)
- [InfoQ: Mixed-Precision Quantization via Global Information Flow](https://mlsanity.com/paper/2508.04753/) (2025)
- [AMED: Automatic Mixed-Precision Quantization for Edge Devices](https://mlsanity.com/paper/2205.15437/) (2022)
- [Accuracy Booster: Enabling 4-bit Fixed-point Arithmetic for DNN Training](https://mlsanity.com/paper/2211.10737/) (2022)
- [Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference](https://mlsanity.com/paper/2301.13330/) (2023)
- [DeepBurning-MixQ: An Open Source Mixed-Precision Neural Network Accelerator Design Framework for FPGAs](https://mlsanity.com/paper/2308.11334/) (2023)

## Abstract (arXiv)

Model quantization helps to reduce model size and latency of deep neural networks. Mixed precision quantization is favorable with customized hardwares supporting arithmetic operations at multiple bit-widths to achieve maximum efficiency. We propose a novel learning-based algorithm to derive mixed precision models end-to-end under target computation constraints and model sizes. During the optimization, the bit-width of each layer / kernel in the model is at a fractional status of two consecutive bit-widths which can be adjusted gradually. With a differentiable regularization term, the resource constraints can be met during the quantization-aware training which results in an optimized mixed precision model. Further, our method can be naturally combined with channel pruning for better computation cost allocation. Our final models achieve comparable or better performance than previous quantization methods with mixed precision on MobilenetV1/V2, ResNet18 under different resource constraints on ImageNet dataset.