mlsanityData to 14 Oct 2026

Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R

arXiv 2507.08505 ↗First posted 11 Jul 2025cs.LGcited by 2

On the map: Multimodal LLMs / vision-language models → Visual token pruning and efficiency

Abstract (arXiv)

Vision-Language Models (VLMs) offer promising capabilities for mobile devices, but their deployment faces significant challenges due to computational limitations and energy inefficiency, especially for real-time applications. This study provides a comprehensive survey of deployment frameworks for VLMs on mobile devices, evaluating llama.cpp, MLC-Imp, and mllm in the context of running LLaVA-1.5 7B, MobileVLM-3B, and Imp-v1.5 3B as representative workloads on a OnePlus 13R. Each deployment framework was evaluated on the OnePlus 13R while running VLMs, with measurements covering CPU, GPU, and NPU utilization, temperature, inference time, power consumption, and user experience. Benchmarking revealed critical performance bottlenecks across frameworks: CPU resources were consistently over-utilized during token generation, while GPU and NPU accelerators were largely unused. When the GPU was used, primarily for image feature extraction, it was saturated, leading to degraded device responsiveness. The study contributes framework-level benchmarks, practical profiling tools, and an in-depth analysis of hardware utilization bottlenecks, highlighting the consistent overuse of CPUs and the ineffective or unstable use of GPUs and NPUs in current deployment frameworks.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 10 of its 16 references that are in the map. First posted on arXiv 11 Jul 2025.

Builds on

10 of 16 references.

References · 10

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  4. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  5. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 572
  6. 2024Large Multimodal Agents: A Surveycited by 105
  7. 2024PowerInfer-2: Fast Large Language Model Inference on a Smartphonecited by 103
  8. 2024DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perceptioncited by 73
  9. 2023SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budgetcited by 27
  10. 2024Imp: Highly Capable Large Multimodal Models for Mobile Devicescited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compressioncited by 6
  2. 2026Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
  2. 2024MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
  3. 2026Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs
  4. 2024PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
  5. 2026Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment
  6. 2024MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases
  7. 2026Empirical Recipes for Efficient and Compact Vision-Language Models
  8. 2025Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs