Run fast, private agents on-device with LFM2.5-24B-A2B

Hugging Face has released LFM2.5-24B-A2B, a machine learning model designed to perform autonomous agent tasks locally on consumer hardware. By enabling private, on-device processing, the model allows users to execute complex digital workflows without transmitting sensitive data to external servers. This release targets developers seeking a balance between high-performance reasoning capabilities and the security benefits of local execution.