FrontierThe story, in brief
Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
JetBrains just shipped Mellum2: a 12B MoE model. Here's why it matters for code generation.
The KeyNews take
Why it matters
JetBrains enters the open-source model space with a specialized Mixture-of-Experts architecture, signaling how major developer-tool companies are building proprietary AI capabilities rather than relying solely on third-party models.
The key facts
5 to knowMellum2: 12B parameter Mixture-of-Experts model
Released by JetBrains on Hugging Face
Published June 1, 2026
MoE architecture suggests efficiency focus for inference/deployment
Developer tool company entering open-source model space
Go to the source
Hugging Face Bloghuggingface.co