Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents

Liquid AI has released LFM2.5-24B-A2B, an open-weight model that uses a mixture-of-experts architecture to activate only 2 billion parameters at a time. Designed for on-device applications, the model achieves 184 tokens per second on an Apple M5 Max while maintaining a reasoning score of 48.09 on the LiveCodeBench benchmark.