1.2b

Last updated on February 17, 2026 by Editorial Team Author(s): mohammedabdelmenem Originally published on Towards AI. Forget GPT-5 for agent tasks. LFM 2.5 runs at 359 tokens/second in 900MB. Here’s …

Liquid AI has released LFM2.5-1.2b-Thinking, a 1.2 billion parameter reasoning model that runs entirely on device and fits in about 900 MB on a modern phone. What was required in …