
Liquid Debuts LFM2.5-2.6B: Local AI for Edge Devices
Liquid AI has launched LFM2.5-2.6B, an open-weight language model designed for agentic workloads that can run entirely on local hardware without relying on cloud inference or GPUs. This is significant for developers working in environments with limited connectivity or high-volume tasks where real-time processing is crucial. The model contains 2.6 billion parameters and supports a massive 128,000-token context window, making it ideal for robotics, vehicles, and other edge devices. It runs well on CPUs, offering decoding throughput of approximately 220 tokens per second on an Apple M5 Max and 113 tokens per second on an AMD Ryzen AI Max+ 395.







