Run fast, private agents on-device with LFM2.5-24B-A2B
Source
huggingface.co
Date
Why it matters
A reasoning modelA model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.Full definition → with only 2B active parameters runs at 184 tok/s on an M5 Max and works inside popular agent harnesses. It makes continuous local agents more practical for privacy-sensitive or offline setups.
Terms in this piece · Glossary
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
