---
title: "JetBrains Opens Mellum2 Thinking, a 12B Coding Model Built for Agentic AI Speed"
subtitle: "JetBrains released Mellum2 Thinking, a 12B Mixture-of-Experts model with 2.5B active parameters, built for low-latency reasoning inside agentic coding pipelines."
url: "https://alphasignal.ai/news/jetbrains-opens-mellum2-thinking-a-12b-coding-model-built-for-agentic-ai-speed"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-05-26T09:12:25.000Z"
updated: "2026-06-05T20:26:19.060Z"
type: "Model"
topics:
  - "Reasoning"
  - "Llms"
subtopics:
  - "Test Time Compute"
  - "Math Reasoning"
  - "Mixture Of Experts"
upvotes: 4066
source_url: "https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Thinking"
comments: 0
truncated: true
---

# JetBrains Opens Mellum2 Thinking, a 12B Coding Model Built for Agentic AI Speed

> JetBrains released Mellum2 Thinking, a 12B Mixture-of-Experts model with 2.5B active parameters, built for low-latency reasoning inside agentic coding pipelines.

JetBrains has open-sourced [Mellum2 Thinking](https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Thinking), a 12-billion-parameter Mixture-of-Experts model that activates only 2.5B parameters per token and emits explicit chain-of-thought traces before answering. It is the reasoning sibling in a six-checkpoint family aimed squarely at the plumbing of agentic AI systems: routing, retrieval, sub-agents, and code-heavy workloads that have to run on your own hardware.

The pitch is unusual. Rather than chase frontier benchmarks, JetBrains is positioning Mellum2 as what they call a [focal model](https://huggingface.co/blog/JetBrains/mellum2-launch), optimized for the high-frequency, latency-sensitive calls that pile up around a larger reasoning model. A single frontier model can be powerful, but production systems often need several specialized components working together: retrievers, routers, code-aware models, validators, tool callers, and larger reasoning models, and JetBrains thinks of Mellum2 as a focal model: a fast, well-scoped model optimized for high-frequency tasks inside larger AI systems.

## What shipped

JetBrains published the Mellum 2 family on Hugging Face as a Mixture-of-Experts coding model at 12B total parameters with 2.5B active per token, released under Apache 2.0, with six variants shipping simultaneously: Base, Base-Pretrain, Instruct, Instruct-SFT, Thinking, and Thinking-SFT. The Thinking variant is the one most teams will reach for when they want the model to deliberate.

The headline architecture numbers:

* A Mixture-of-Experts architecture with 64 experts that activates 8 experts per token, combined with sliding-window and full attention layers, and a context length of 131,072 tokens.

_Preview only. Full text requires an AlphaSignal Pro account._