AI article
Run fast, private agents on-device with LFM2.5-24B-A2B
No preview is available. Read the original article for the full story.
huggingface | Oct 13, 2026 | Raahul Vignesh, Song Duong, Akhilesh Deepak Gotmare, Fernando Fernandes Neto, Jiahui Wang, Mayank Agarwal, nathan ranchin, Sergei Tilga, Sinoué GAD, Tim Seyde, Zetian Li, changyi yang, Simon Lee, Leonie Monigatti, Maxime Labonne
Automated excerpt
LFM2. 5-24B-A2B is a 24B-parameter reasoning model with just 2B active parameters, built for fast, private agents on-device. With only 2B active parameters per token, each reasoning token is cheap. Agentic reinforcement learning (Agentic RL): train the model inside agent harnesses, such as OpenClaw, Hermes Agent, Pi, and OpenCode.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.