Vibeleaderboard
← All Intel
Intel / article

LFM2.5-24B-A2B: Built for fast on-device agents

Source
liquid.ai
Author
gmays
Date
Why it matters

An model with 2B active parameters runs at 184 tokens/s on an M5 Max and was trained inside harnesses. It gives local-agent builders a faster, private option.

Terms in this piece · Glossary
  • open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
  • 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.
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Read the source www.liquid.ai
More from gmays
Recommended reads
Comments

Checking sign-in…

Loading comments…