Tendem
Mini toolsLFM2 VL 3B
By Liquid AI
LFM2-VL-3B pairs a compact language backbone with a strong vision encoder so it can look, read, and reason in one pass. You can provide documents, receipts, dashboards, UI screenshots, or photos alongside a prompt, and it extracts small text, keeps layout and relationships intact, and returns grounded explanations or schema-true JSON that downstream systems can parse. Multi-image threads stay coherent, references to specific regions are supported when you need evidence, and the model integrates with tool or function calling for crops, retrieval, or validation inside an agent loop. Its 3B scale is tuned for speed and cost without giving up reliability, and long-context prompting keeps multi-page jobs on track. Teams use LFM2-VL-3B for document automation, chart and table understanding, screenshot helpers, multimodal search, and developer copilots that need vision with predictable latency and clean integration.
New
Text
Gen 7
Overview
LFM2-VL-3B is a 3B vision-language model that reads images with text and answers in natural language or structured JSON. It handles OCR, charts, tables, and screenshots with long context and low-latency streaming, making it practical for multimodal RAG and assistants.
About Liquid AI
Liquid AI is an MIT spin-off building efficient general-purpose AI models (Liquid Foundation Models, or LFMs) that run on edge devices with less memory and power.
They recently raised $250M in Series A funding to scale model development and deployment.
Website:
liquid.ai
Tools using LFM2 VL 3B
No tools found for this model yet.
Last updated: February 3, 2026
