Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput

In this paper, we introduce Flash-VL 2B, a novel approach to optimizing Vision-Language Models (VLMs) for real-time applications, targeting ultra-low latency and high throughput without sacrificing accuracy. Leveraging advanced architectural enhancements and efficient computational strategies, Flash-VL 2B is designed to maximize throughput by reducing processing time while maintaining competitive performance across multiple vision-language benchmarks. Our approach includes tailored architectural choices, token compression mechanisms, data curation, training schemes, and a novel image processing technique called implicit semantic stitching that effectively balances computational load and model performance. Through extensive evaluations on 11 standard VLM benchmarks, we demonstrate that Flash-VL 2B achieves state-of-the-art results in both speed and accuracy, making it a promising solution for deployment in resource-constrained environments and large-scale real-time applications.

@article{zhang2025_2505.09498,
  title={ Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput },
  author={ Bo Zhang and Shuo Li and Runhe Tian and Yang Yang and Jixin Tang and Jinhao Zhou and Lin Ma },
  journal={arXiv preprint arXiv:2505.09498},
  year={ 2025 }
}