QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models

TL;DR

This paper introduces a quantization-aware vision token pruning method for multimodal large language models, improving low-bit inference accuracy by jointly optimizing token relevance and quantization stability.

Contribution

It proposes a hybrid sensitivity metric that combines quantization error and outlier intensity to effectively co-optimize token pruning and quantization.

Findings

Outperforms naive token pruning and quantization baselines.

Achieves 2.24% accuracy gain at 12.5% token retention.

Surpasses dense quantization without pruning in low-bit regimes.

Abstract

Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings. While Post-Training Quantization (PTQ) and vision token pruning are standard compression techniques, they are usually treated as independent optimizations. In this paper, we show that these two techniques are strongly coupled: naively applying semantic-based token pruning to PTQ-optimized MLLMs can discard activation outliers that are important for numerical stability and thus worsen quantization errors in low-bit regimes (\textit{e.g.}, W4A4). To address this issue, we propose a quantization-aware vision token pruning framework. Our method introduces a lightweight hybrid sensitivity metric that combines simulated group-wise quantization error with outlier intensity. By combining this metric with standard semantic relevance scores, the method retains tokens that are both semantically informative and robust to quantization. Experiments on standard LLaVA architectures show that our method consistently outperforms naive integration baselines. At an aggressive pruning ratio that retains only 12.5\% of visual tokens, our framework improves accuracy by 2.24\% over the baseline and even surpasses dense quantization without pruning. To the best of our knowledge, this is the first method that explicitly co-optimizes vision token pruning and PTQ for accurate low-bit MLLM inference.