MagenticLite is officially live on GitHub, with models available on Microsoft Foundry.
We’ve optimized the entire stack end-to-end to deliver a faster, more efficient agentic experience powered entirely by small language models.
What powers this end-to-end harness:
Fara1.5: Our computer-use model family (4B, 9B, 27B). The 9B flagship nearly doubles Fara-7B on web navigation, setting a new SOTA for small computer-use models.
MagenticBrain: A 14B orchestrator model that plans, codes, and delegates.
