LFM2.5-2.6B: On-Device Agents

Liquid AI released LFM2.5-2.6B, a 2.6B dense model for on-device agentic workloads with a 128K context window and native tool calling, designed to run on edge devices and integrate with agent harnesses like Hermes Agent, OpenClaw, and Pi.

← Back to Text Models /lfm/models/text-models LFM2.5-2.6B is Liquid AI’s 2.6B dense model built for agentic workloads with a 128K context window and native tool calling. It runs on edge devices and it is trained to work reliably inside agent harnesses like Hermes Agent, OpenClaw, and Pi. Specifications Agentic & Tool Use Native tool calling, trained inside real agent harnesses 128K Context Long context for tool traces and multi-step workflows On-device Small enough to run on a laptop or phone Quick Start - Transformers - llama.cpp - vLLM - SGLang