No cloud, no GPUs: Liquid AI's LFM2.5-2.6B model empowers edge devices
Liquid AI introduces LFM2.5-2.6B, a model that runs on local hardware without cloud or GPU dependencies.
Liquid AI, a startup founded by former MIT scientists, has launched LFM2.5-2.6B, a new open-weight language model designed for local hardware use. Capable of running on devices from smartphones to Raspberry Pi without cloud reliance, it opens new possibilities for edge AI applications, particularly for enterprises with sensitive data. The model is optimized for agentic tasks, offering a cost-effective solution for businesses looking to leverage AI locally.