No cloud, no GPUs, no problem: Liquid AI's new model LFM2.5-2.6B brings powerful AI agents to devices as small as a Raspberry Pi

Liquid AI debuted LFM2.5-2.6B, a 2.6B-parameter open-weight language model built for local agentic workloads such as tool calling, document handling, workflow automation, and always-on routines. The model supports a 128K-token context window, runs without cloud inference or GPUs, and is available on Hugging Face with support for major inference stacks.

The release reflects a broader shift toward edge AI, where smaller specialized models handle high-volume tasks cheaply and privately on local hardware. Enterprises in regulated or connectivity-limited environments may benefit, though legal teams will need to scrutinize Liquid’s custom open-weight license before deployment.