LFM2.5-2.6B + Hermes Agent: A Coding Agent That Runs Entirely On-Device

LFM2.5-2.6B is a 2.6B parameter agentic model small enough to run on a phone, fast enough to stay responsive on a CPU, and capable enough to power agentic workflows: planning, calling tools, and tackling multi-step tasks. In this demo, we run LFM2.5-2.6B inside Hermes Agent entirely on-device. Because there's no per-token cost, agents like this can run in parallel, around the clock, at zero marginal cost. Get the models:  https://huggingface.co/LiquidAI/LFM2.5-2.6B Read the full release: https://www.liquid.ai/blog/lfm2-5-2-6b