Liquid AI

LFM LFM2.5-2.6B is a 2.6 billion parameter open weight language model built for agentic workflows. It handles planning, tool calling, and multi step tasks, with a 128K context window for long inputs and an expanded 128K…

• 💬 Chatting
• 📚 Large Language Models
• 💻 Coding
• 🤖 Agents
• 🔍 Advanced reasoning
• 🔢 Math New

LFM LFM2.5-230M is a 230M-parameter lightweight language model built on the LFM2 architecture, designed for fast inference across edge and cloud environments. Pre-trained on 19T tokens with a 32K context window, it targ…

• 🤖 Task automation
• 📚 Large Language Models
• 🤖 Agents
• 🤖 Robotics New

LFM 350M-parameter bidirectional multilingual bi-encoder that maps each document to a single dense vector for fast, cost-efficient multilingual and cross-lingual search. Supports 11 languages. Built from LFM2.5-350M-Bas…

• 🔍 Information retrieval
• 🔍 Document search
• 🔍 Conceptual search New

LFM 350M-parameter bidirectional multilingual retrieval model using per-token ColBERT-style late interaction (MaxSim) for accurate multilingual and cross-lingual search. Supports 11 languages. Built from LFM2.5-350M-Bas…

• 🔍 Information retrieval
• 🔍 Document search
• 🔍 Conceptual search New

Liquid AI’s larger vision-language extraction model for image-to-JSON structured field extraction.

• 🔍 Data extraction
• 🔍 Image interpretation
• 📜 OCR

LFM LFM2.5-1.2B-JP-202606 is Liquid AI’s 1.17B Japanese-focused text model for chat, instruction following, math, code, tool use, and bilingual English-Japanese assistant workflows.

• 💬 Chatting
• 🈯️ Japanese content generation

LFM LFM2.5-VL-1.6B-Extract is Liquid AI’s 1.6B vision-language extraction model for image-to-JSON structured field extraction.

• 🔍 Data extraction
• 🔍 Image interpretation
• 📜 OCR

Liquid AI’s compact vision-language model for structured visual intelligence from edge to cloud. It is built to turn image streams into grounded, actionable outputs in real time, adding object grounding, better instruct…

• 🔍 Image interpretation
• 🔍 Image recognition
• 📜 OCR

Liquid AI’s compact 350M-parameter language model optimized for fast inference, tool use, data extraction, and structured outputs. It is designed to run across cloud GPUs, CPUs, and edge devices, and is positioned for l…

• 📚 Large Language Models
• 🔍 Data extraction
• 🔄 Language model optimization
• 🧠 AI inference

A hybrid Mixture-of-Experts language model designed for efficient on-device deployment, scaling to 24B total parameters with a small active parameter set per token.

LFM LFM2.5-1.2B-Thinking is Liquid AI’s 1.2B parameter reasoning-focused variant of its LFM2.5 edge family, optimized for agentic workflows, RAG and data extraction with 32K context, and exposed on OpenRouter as a free…

• 📊 Data analysis
• 🔍 SEO content
• 💼 Freelance job proposals

LFM LFM2.5-1.2B is Liquid AI’s 1.2B hybrid edge model for on-device chat and tools, trained on 28T tokens and RL, running under 1 GB of RAM while rivaling much larger LLMs on reasoning and agentic tasks.

• 💬 Chatting
• 💻 Coding
• 🤖 Chatbots
• 🚀 Productivity