LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models

• URL: http://arxiv.org/abs/2509.23729v2
• Date: Sun, 26 Oct 2025 06:17:42 GMT
• Title: LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models
• Abstract summary: We present the first study on ultra-low bit (4-bit) quantization for multimodal LLMs.<n>Our analysis reveals that multimodal tokens and intermediate layer activations produced by them exhibit significantly higher statistical variance and entropy compared to text tokens.<n>We propose a novel strategy for MLLM quantization, LUQ: Layerwise Ultra-Low Bit Quantization, which applies ultra-low bit quantization to layers that are more resilient to it.
• Score: 8.912472985242575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. While post-training quantization (PTQ) has successfully compressed language models to as low as 1-bit precision without significant performance loss, its effectiveness for multimodal LLMs (MLLMs) remains relatively unexplored. In this paper, we present the first study on ultra-low bit (<4-bit) quantization for multimodal LLMs. Our analysis reveals that multimodal tokens and intermediate layer activations produced by them exhibit significantly higher statistical variance and entropy compared to text tokens, making them less tolerant to ultra-low bit quantization. However, the activation distributions of multimodal tokens varies significantly over different layers, with some layers having lower entropy activation distributions. We empirically show that such layers in these models can better tolerate ultra-low bit quantization. Building on these insights, we propose a novel strategy for MLLM quantization, LUQ: Layerwise Ultra-Low Bit Quantization, which selectively applies ultra-low bit quantization to layers that are more resilient to it. Additionally, we also show that using a mix of multimodal tokens (image and text) for PTQ boosts VQA performance in the ultra-low bit regime. We evaluate our method on LLaVA-1.5 and Qwen-2.5-VL across 9 popular VQA benchmarks. The resulting LUQ models use 40% and 31% less memory than their 4-bit counterparts, respectively, while exhibiting a performance degradation of less than 10% on the MME benchmark.

Related papers

• Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs [14.385983354036142]
  Low-bit quantization offers a promising avenue for reducing the computational and memory demands of Multimodal Large Language Models.<n>Recent hardware support for low-precision formats, such as MXFP8 and ultra-low-bit formats such as MXFP4 and HiF4, has accelerated research into efficient MLLM training and deployment.<n>We present a systematic study of these quantization schemes in representative MLLMs that span both video generation and reasoning tasks.
  arXiv  Detail & Related papers  (2026-08-27T03:47:58Z)
• LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation [29.676785178178104]
  We present LBLLM, a lightweight binarization framework that achieves W(1+1)A4 quantization through a novel three-stage quantization strategy.<n>LBLLM, trained only using 0.016B tokens with a single GPU, surpasses existing state-of-the-art binarization methods on W2A4 quantization settings.
  arXiv  Detail & Related papers  (2026-04-21T07:25:02Z)
• LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution [52.627063566555194]
  We introduce LSGQuant, a layer-sensitivity guided quantizing approach for one-step diffusion-based real-world VSR.<n>Our method incorporates a Dynamic Range Adaptive Quantizer (DRAQ) to fit video token activations.<n>Our method has nearly performance to origin model with full-precision and significantly exceeds existing quantization techniques.
  arXiv  Detail & Related papers  (2026-02-03T06:53:19Z)
• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs [78.09559830840595]
  We present the first systematic study on quantizing diffusion-based language models.<n>We identify the presence of activation outliers, characterized by abnormally large activation values.<n>We implement state-of-the-art PTQ methods and conduct a comprehensive evaluation.
  arXiv  Detail & Related papers  (2025-08-20T17:59:51Z)
• VLMQ: Efficient Post-Training Quantization for Large Vision-Language Models via Hessian Augmentation [8.891793681316992]
  Post-training quantization (PTQ) has emerged as an effective approach for compressing large models and accelerating their inference without retraining.<n>While PTQ has been extensively studied in the context of large language models (LLMs), its applicability to vision-language models (VLMs) remains underexplored.<n>We propose a novel importance-aware PTQ framework tailored for VLMs, dubbed VLMQ.
  arXiv  Detail & Related papers  (2025-08-05T11:57:03Z)
• Quantizing Large Language Models for Code Generation: A Differentiated Replication [51.85505914274633]
  Large Language Models (LLMs) have shown an impressive capability in code generation and, specifically, to automatically implement requirements described in natural language.<n>LLMs pose significant challenges related to their memory (and, consequently, carbon) footprint.<n>New frontier for LLM quantization is 4-bit precision, resulting in an average memory footprint reduction of 70%.
  arXiv  Detail & Related papers  (2025-03-10T09:26:08Z)
• MBQ: Modality-Balanced Quantization for Large Vision-Language Models [20.018652727875367]
  Post-Training Quantization (PTQ) is an effective technique to reduce the memory and computation overhead.<n>Existing PTQ methods mainly focus on large language models (LLMs), without considering the differences across other modalities.<n>We propose Modality-Balanced Quantization (MBQ) for large vision-language models.
  arXiv  Detail & Related papers  (2024-12-27T07:55:36Z)
• Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation [70.22782550540714]
  Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW. We introduce a Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW.
  arXiv  Detail & Related papers  (2024-08-07T12:42:09Z)
• Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels [20.706177044867797]
  We present a simple meta quantization approach that quantizes different layers of a large language model (LLM) at different bit levels. Specifically, we quantize the most important layers to higher bit precision and less important layers to lower bits.
  arXiv  Detail & Related papers  (2024-06-25T09:37:15Z)
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [63.118592279833656]
  Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs)<n>We propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise.<n> Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths.
  arXiv  Detail & Related papers  (2024-05-23T16:21:48Z)
• An empirical study of LLaMA3 quantization: from LLMs to MLLMs [54.91212829143966]
  The LLaMA family is one of the most powerful open-source large language models (LLMs)<n>LLaMA3 models have achieved impressive performance in various domains with super-large scale pre-training on over 15T tokens of data.<n>We evaluate the 10 existing post-training quantization and LoRA fine-tuning (LoRA-FT) methods of LLaMA3 on 1-8 bits and various datasets to reveal the low-bit quantization performance of LLaMA3.
  arXiv  Detail & Related papers  (2024-04-22T10:03:03Z)
• DB-LLM: Accurate Dual-Binarization for Efficient LLMs [83.70686728471547]
  Large language models (LLMs) have significantly advanced the field of natural language processing. Existing ultra-low-bit quantization always causes severe accuracy drops. We propose a novel Dual-Binarization method for LLMs, namely DB-LLM.
  arXiv  Detail & Related papers  (2024-02-19T09:04:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.