Liquid AI's Labonne: Stop Using Free LFM2.5-2.6B for Coding, It's Not Built for It

maximelabonne · x · 2026-09-15

Liquid AI's Maxime Labonne jokingly urged users to stop using LFM2.5-2.6B for coding, then said 'I'm kidding, break stuff with it for free.' The OpenRouter listing confirms why: the free 2.6B reasoning model (15.4B tokens processed) is suited for agent workflows, data extraction, RAG and long-context tasks, but Liquid explicitly advises against it for agentic coding or knowledge-heavy work. The family also includes free LFM2.5-Embedding-350M, the on-device 24B MoE LFM2-24B-A2B (2B active params, fits in 32GB RAM), and LFM2.5-1.2B-Thinking. Free-tier prompts and outputs may be used for training.

Related event: Liquid AI Warns: Don't Use LFM2.5-2.6B for Coding(2 posts)→

Original post →

More from Models

Models channel →