LFM2.5-VL-3B: Document OCR and Layout Understanding in WebGPU

This demo shows Liquid AI's LFM2.5-VL-3B running fully on-device in the browser with WebGPU to understand a document page. Given an uploaded document, the model parses the entire layout in one pass and returns regions and labels that the interface renders as an overlay. The demo highlights OCR and layout understanding for visually structured content such as forms, reports, receipts, and other documents. LFM2.5-VL-3B is a 3-billion-parameter general-purpose vision-language model built for fast, real-time, and on-device applications. 🔗 Links: • WebGPU demo: https://huggingface.co/spaces/LiquidAI/LFM2.5-VL-3B-WebGPU • Model: https://huggingface.co/LiquidAI/LFM2.5-VL-3B • Blog post: https://www.liquid.ai/blog/lfm2-5-vl-3b • Documentation: https://docs.liquid.ai/lfm/models/lfm25-vl-3b • Playground: http://playground.liquid.ai/chat?model=lfm2.5-vl-3b Connect with Liquid AI: • Careers: https://www.liquid.ai/careers • Hugging Face: https://huggingface.co/LiquidAI • Discord: https://discord.com/invite/liquid-ai • X: https://x.com/LiquidAI • LinkedIn: https://www.linkedin.com/company/liquid-ai-inc/ • GitHub: https://github.com/Liquid4All/cookbook • Substack: https://liquidai.substack.com/