kapynAI / Models

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

LFM2.5-24B-A2B is a lightweight, private agent model that runs on-device. It contains 24 billion parameters and uses an A2B architecture for efficient inference. Developers can deploy it on edge devices without sending data to the cloud, enabling privacy‑first applications.

Hugging Face·Oct 13, 2026

Opening Kapyn…