Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation

About

Quantization has emerged as a mainstream approach for deploying Large Language Models (LLMs) on resource-constrained devices, yet compressing precision below 4-bit typically causes severe performance degradation or prohibitive retraining costs. In this paper, we propose EdgeRazor, a lightweight framework for LLMs via Mixed-Precision Quantization-Aware Distillation. It contains three modules: Structural Quantization with Mixed Precision for fine-grained control of bit-widths, Layer-Adaptive Feature Distillation that dynamically selects the most informative features for alignment, and Entropy-Aware KL Divergence for forward-reverse balance on both human-annotated and distilled datasets. Evaluations conducted on MobileLLM and Qwen families show that under weight-activation quantization, the 1.88-bit Qwen3-0.6B-EdgeRazor outperforms the state-of-the-art 2-bit baselines by 11.27 and surpasses the strongest 3-bit baselines by 4.38, while the quantized MobileLLM-350M-EdgeRazor requires a training budget 4-10$\times$ lower than the leading quantization-aware training method. In terms of efficiency, EdgeRazor achieves higher compression ratios at all bit-widths, and the 1.58-bit Qwen3-0.6B-EdgeRazor reduces storage from 1.11 GB to 0.19 GB while accelerating decoding by 15.16$\times$ over the 16-bit baseline. These results empirically validate the effectiveness and efficiency of EdgeRazor. The codes can be accessed from \href{https://github.com/zhangsq-nju/EdgeRazor}{GitHub} and \href{https://huggingface.co/collections/zhangsq-nju/edgerazor-nbit}{Huggingface}.

Shu-Hao Zhang, Le-Tong Huang, Xiang-Sheng Deng, Xin-Yi Zou, Chen Wu, Nan Li, Shao-Qun Zhang, Zhi-Hua Zhou• 2026

Related benchmarks

TaskDatasetResultRank
Large Language Model EvaluationQwen3-0.6B Average (test)
Average Performance47.83
38
LLM EvaluationQwen3-1.7B Evaluation Suite (avg)
Average Performance58.56
38
Language Model EvaluationQwen3-0.6B Evaluation Suite average
Average Performance47.8
24
Multimodal Language UnderstandingQwen3 1.7B
Average Performance58.57
24
Zero-shot EvaluationMobileLLM Evaluation Suite zero-shot
ARC-e69.19
23
Model CompressionQwen3-0.6B
Compression Ratio7.03
13
Zero-shot Language Model EvaluationMobileLLM Evaluation Suite zero-shot 350M
Average Performance41.86
11
Large Language Model InferenceQwen3-0.6B (inference)
Storage (GB)0.255
6
Video UnderstandingMLVU
MLVU Score48.82
4
Video UnderstandingVideo-MME
Video-MME Score62.22
4
Showing 10 of 10 rows

Other info

Follow for update