← Back to Text ModelsLFM2.5-2.6B 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
source & further reading
docs.liquid.ai — original article