Skip to content
NewA calmer, faster ZeroHour

JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents

MarkTechPostby Asif Razzaq ()4
AI summary · grok-4.7Summaries by Vani AI

JetBrains released Mellum2.1, an Apache 2.0 12B MoE coding model with 2.5B active parameters.

JetBrains released Mellum2.1, an Apache 2.0 mixture-of-experts thinking model with 12 billion total parameters and 2.5 billion active parameters. Reinforcement learning on real repositories lifted its SWE-bench Verified score from 2.0 to 47.0. The open model is aimed at coding agents.

Key facts
  • Mellum2.1 is Apache 2.0 with 12B total and 2.5B active parameters.
  • Repository reinforcement learning raised SWE-bench Verified from 2.0 to 47.0.
  • JetBrains positions the mixture-of-experts thinking model for coding agents.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

JetBrains released Mellum2. 1, an Apache 2. 0, 12B mixture-of-experts thinking model with 2.

MarkTechPost

By Asif Razzaq · marktechpost.com

Read the full article at MarkTechPost

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.