LFM2.5-1.2B-Instruct

LFM2.5-1.2B-Instruct is Liquid AI’s compact 1.2B-parameter instruction model built for efficient text generation, conversational AI, and lightweight agent workflows. It supports native tool calling and multilingual use, while its small footprint makes it well suited for low-latency inference on edge devices and resource-constrained environments. It is a strong fit for chat, simple assistants, instruction following, routing, and high-volume agent tasks where speed, efficiency, and cost matter more than deep reasoning.