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
Earlier this week, the AI startup Liquid, formed in 2023 by former MIT computer scientists, debuted LFM2.5-2.6B , a new open-weight language model designed specifically for agentic workloads. In release materials and a recent interview with VentureBeat, Liquid's researchers said LFM2.5-2.6B can run entirely on local hardware — from smartphones and laptops down to a Raspberry Pi — without relying…
Liquid AI, a startup founded in 2023 by former MIT computer scientists, has introduced LFM2.5-2.6B, a new open-weight language model specifically designed for agentic workloads. This model can run entirely on local hardware, such as smartphones, laptops, and even a Raspberry Pi, without relying on cloud inference or GPUs. This capability opens up new possibilities for edge AI applications, particularly for high-volume, well-defined tasks like tool calling, document management, and workflow automation.
The model's open weights license also provides enterprises with greater flexibility, especially in regulated industries or with sensitive information that they prefer not to send to the cloud.
Brief written by urgent.news from VentureBeat's own syndicated text. Machine-written — it may contain errors, so check the original before relying on it.
