aiqbench analysis
JetBrains has open-sourced Mellum2, a 12B parameter Mixture-of-Experts model optimized for specialized software engineering tasks within larger multi-model pipelines rather than as a standalone frontier model. The architecture utilizes 2.5B active parameters per token with 64 experts to maintain low compute costs while supporting a 131k context window and speculative decoding. Released under Apache 2.0, this model offers a practical, efficient option for integrating high-capacity code reasoning capabilities into existing developer workflows.
JetBrains Releases Mellum2: A 12B MoE Model for Fast, Specialized Tasks in Multi-Model AI Pipelines
JetBrains releases Mellum2 under Apache 2.0 — a 12B MoE model trained on 10.6 trillion tokens for AI workflows. The post JetBrains Releases Mellum2: A 12B MoE Model for Fast, Specialized Tasks in Multi-Model AI Pipelines appeared first on MarkTechPost.
JetBrains released Mellum2, open-sourcing the weights under the Apache 2.0 license. The first version of Mellum was a completion-focused 4B dense model. Mellum2 is its successor: a general-purpose model specialized in software engineering. It covers code generation and editing, debugging, multi-step reasoning, tool use and function calling, agentic coding, and conversational programming assistance. JetBrains team positions Mellum2 as a “focal model” — a fast, specialized component inside larger AI systems, not a standalone replacement for frontier models.…
Excerpt shown under the publisher's RSS terms · 77 words · full text and figures are on the publisher's site
Related coverage
Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
Hugging Face · Jun 1, 2026
Presentation: What 25 Trillion Tokens Reveal About How Developers Actually Adopt AI Agents
InfoQ · Oct 15, 2026
Introducing Claude Opus 5
Anthropic · Jul 24, 2026
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
Latent Space · Sep 9, 2026