Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs

• URL: http://arxiv.org/abs/2608.21134v1
• Date: Fri, 21 Aug 2026 14:10:31 GMT
• Title: Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs
• Abstract summary: We present a framework for quantizing vision-language models (VLMs) for efficient inference on resource-constrained hardware.<n>Our approach combines a quantization pipeline that uses the model itself to generate training data and does not require access to the training setup.<n>We validate our approach by compressing the Llama 3.2 11B Vision Instruct model to 3.7 GB with 8-bit activations.
• Score: 2.851131916285667
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Deploying vision-language models (VLMs) on mobile devices is challenging due to their significant memory and compute requirements. We present a framework for quantizing VLMs for efficient inference on resource-constrained hardware. Our approach combines a quantization pipeline that uses the model itself to generate training data and does not require access to the training setup, with a novel 2.7-bit-per-parameter format supporting efficient execution on Arm CPUs. We validate our approach by compressing the Llama 3.2 11B Vision Instruct model to 3.7 GB with 8-bit activations, preserving strong performance on a set of standard visual question answering tasks.

Related papers

• LFM2 Technical Report [87.58431408281973]
  We present LFM2, a family of Liquid Foundation Models designed for efficient on-device deployment and strong task capabilities.<n>The LFM2 family covers 350M-8.3B parameters, including dense models (350M, 700M, 1.2B, 2.6B) and a mixture-of-experts variant (8.3B total, 1.5B active)<n>We build multimodal and retrieval variants: LFM2-VL for vision-latency tasks, LFM2-Audio for speech, and LFM2-ColBERT for retrieval.
  arXiv  Detail & Related papers  (2025-11-28T17:56:35Z)
• VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment [88.83260031198023]
  We propose a vision-encoder-centered generative pre-training pipeline and develop the VITAL-Series LMMs.<n>We construct over 4.5M vision-language (VL) pairs-the largest VQualA training dataset to date.<n>We employ a multi-task training workflow that simultaneously enhances the model's quantitative scoring precision.
  arXiv  Detail & Related papers  (2025-11-22T07:55:21Z)
• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe [68.04078852416248]
  MiniCPM-V 4.5 is an 8B parameter model designed for high efficiency and strong performance.<n>We introduce three core improvements in model architecture, data strategy and training method.<n>MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size.
  arXiv  Detail & Related papers  (2025-09-16T19:41:48Z)
• MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs [20.842336447426682]
  MindVL is a multimodal large language model trained end-to-end on Ascend NPUs.<n>We introduce MindSpeed-MLLM, a highly efficient training framework that supports stable and high-performance training.<n>We find that averaging weights from checkpoints trained with different sequence lengths is particularly effective.
  arXiv  Detail & Related papers  (2025-09-15T08:00:31Z)
• Scene-Aware Vectorized Memory Multi-Agent Framework with Cross-Modal Differentiated Quantization VLMs for Visually Impaired Assistance [4.6432462796838125]
  This study proposes a cross-modal differiated quantization framework for vision-language models (VLMs) and a scene-aware vectorized memory multi-agent system for visually impaired assistance.<n>The modular framework was developed implementing differentiated processing strategies, effectively reducing memory requirements from 38GB to 16GB while maintaining model performance.
  arXiv  Detail & Related papers  (2025-08-25T16:32:32Z)
• MiniCPM4: Ultra-Efficient LLMs on End Devices [126.22958722174583]
  MiniCPM4 is a highly efficient large language model (LLM) designed explicitly for end-side devices.<n>We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.
  arXiv  Detail & Related papers  (2025-06-09T16:16:50Z)
• APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval [41.81696346270799]
  Current large language models (LMs) struggle with hour-level video understanding.<n>bftextAdaptive textbfPivot MLbfVisual information textbfRetrieval (textbfAPVR), a training-free framework that hierarchically retrieves and retains sufficient and important visual information.
  arXiv  Detail & Related papers  (2025-06-05T12:27:10Z)
• TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler [10.92767902813594]
  We introduce TinyLLaVA-Video, a lightweight yet powerful video understanding model with approximately 3.6B parameters.<n>The cornerstone of our design is the video-level group resampler, a novel mechanism that significantly reduces and controls the number of visual tokens at the video level.<n>TinyLLaVA-Video demonstrates exceptional efficiency, requiring only one day of training on 8 A100-40G GPUs.
  arXiv  Detail & Related papers  (2025-01-26T13:10:12Z)
• Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model [51.83436609094658]
  We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T17:57:12Z)
• QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection [57.019527599167255]
  Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. We show in our paper that directly applying quantization in BEV tasks will 1) make the training unstable, and 2) lead to intolerable performance degradation. Our method QD-BEV enables a novel view-guided distillation (VGD) objective, which can stabilize the quantization-aware training (QAT) while enhancing the model performance.
  arXiv  Detail & Related papers  (2023-08-21T07:06:49Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)

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.