# FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization

arXiv: https://arxiv.org/abs/2506.12024 · HTML: https://mlsanity.com/paper/2506.12024/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 16 of 16)

- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks](https://mlsanity.com/paper/2402.04396/) (2024)
- [SqueezeLLM: Dense-and-Sparse Quantization](https://mlsanity.com/paper/2306.07629/) (2023)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [DialogSum: A Real-Life Scenario Dialogue Summarization Dataset](https://mlsanity.com/paper/2105.06762/) (2021)
- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices](https://mlsanity.com/paper/2312.16886/) (2023)
- [KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization](https://mlsanity.com/paper/2405.03917/) (2024)
- [Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs](https://mlsanity.com/paper/2402.10517/) (2024)
- [Progressive Mixed-Precision Decoding for Efficient LLM Inference](https://mlsanity.com/paper/2410.13461/) (2024)
- [Efficient LLMs with AMP: Attention Heads and MLP Pruning](https://mlsanity.com/paper/2504.21174/) (2025)
- [T'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization](https://mlsanity.com/paper/2503.09657/) (2025)

## Built on by (most cited first, 5 of 5)

- [What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study](https://mlsanity.com/paper/2601.14888/) (2026)
- [P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats](https://mlsanity.com/paper/2511.06838/) (2025)
- [P/D-Device: Disaggregated Large Language Model between Cloud and Devices](https://mlsanity.com/paper/2508.09035/) (2025)
- [SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models](https://mlsanity.com/paper/2602.01027/) (2026)
- [HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures](https://mlsanity.com/paper/2602.00748/) (2026)

## Abstract (arXiv)

The rapid advancement of large language models (LLMs) has exacerbated the memory bottleneck due to the widening gap between model parameter scaling and hardware capabilities. While post-training quantization techniques effectively reduce memory overhead, existing methods predominantly rely on static quantization strategies, which struggle to adapt to dynamic workloads. To address this, we propose FlexQuant, a dynamic precision-switching framework that optimizes the trade-off between inference speed and accuracy. Leveraging model perplexity entropy and Kullback-Leibler divergence, FlexQuant enables fine-grained, layer-wise mixed-precision quantization and dynamically adjusts bit-widths during each token generation. FlexQuant provides a comprehensive analysis of quantization strategies, introduces a precision requirement model for optimal switching, and implements efficient fine-grained precision management. Evaluations demonstrate that FlexQuant achieves a 1.3x end-to-end speedup across diverse language tasks with negligible accuracy loss introduced. This framework offers a flexible and adaptive solution for efficient LLM deployment. Code is released at https://github.com/ZongwuWang/FlexQuant.git.