Liquid AI announced the LFM2.5-24B-A2B model, designed for low-latency inference on edge devices. The model aims to enable developers to run sophisticated agents locally without relying on cloud APIs, which can reduce response times and improve privacy. This could be useful for building AI-enhanced front-end tools or offline developer assistants.
Liquid AI releases LFM2.5-24B-A2B for fast on-device agentsliquid.ai ↗