Dev48
Language
  • About
  • Services
  • Industries
  • Technologies
  • Articles
  • Contacts
Book a call
    Home/Articles/Mellum21 gets to work a fast open model for coding agents
Dev48
info@dev48.org+375 29 320-40-96WhatsApp@isky_by

© 2026 · All rights reserved.

Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents

Source: The JetBrains Blog•October 8, 2026 at 02:19 PM

Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents

Trained with reinforcement learning in real environments, Mellum2.1 is built for coding agents and fast sub-agents that run on your own hardware. Today, we’re releasing Mellum2.1, the next version of the 12B mixture-of-experts model we open-sourced in June. The architecture hasn’t…

Supercharge your tools with AI-powered features inside many JetBrains products

News Releases

Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents

Trained with reinforcement learning in real environments, Mellum2.1 is built for coding agents and fast sub-agents that run on your own hardware.

Today, we’re releasing Mellum2.1, the next version of the 12B mixture-of-experts model we open-sourced in June. The architecture hasn’t changed since version 2: it’s still a compact, fast model with 2.5B active parameters, released under the Apache 2.0 license. What has changed is everything that happens after pre-training.

Mellum2 was fast, but it couldn’t work inside a repository at the level we wanted. After a summer of reinforcement learning in real environments, with millions of sandboxed runs across thousands of environments, Mellum2.1 can: it explores a codebase, edits files, and checks its own changes.

Try Mellum

The changes we made in Mellum2.1

Almost all of the work for this version went into post-training, primarily reinforcement learning (RL).

  • Reinforcement learning at a new scale: RL went from a short final stage to the main part of training. We ran many experiments on how to train both the methods and the data, and we kept what held up.
  • More data, filtered harder: We added new RL tasks in math, competitive programming, science, tool use, and software engineering, combining open RL datasets with tasks we built ourselves. Open data often comes with broken tests, unverifiable answers, or tasks that are too easy or impossible for the model, so every source was filtered before it reached training.
  • Real environments for agentic skills: We built the infrastructure to run thousands of RL environments in-house and launched millions of sandboxes over the course of training.

How Mellum2.1 performs

We compared Mellum2.1 with Mellum2 – as well as two open models of a similar class, Qwen3.5-9B and Gemma 4 E4B – using the same evaluation setup for all of them.

The biggest improvement is in agentic coding, where Mellum2.1 advanced the most compared with Mellum2. The model also got better across the board, showing gains in coding, competitive programming, math, tool calling, and general knowledge, and it holds up on hard problems as well as everyday ones.

Speed

Post-training didn’t touch the architecture, so Mellum2.1 is as fast as Mellum2, and multi-token prediction (MTP) makes it faster.

Under heavy load, Mellum2.1 is the fastest model in the group and serves almost twice as many tokens as Qwen3.5-9B. For a single request, MTP makes it about 1.6 times faster.

Key use cases for Mellum2.1

  • A capable worker inside agentic systems: Mellum2.1 can handle different parts of an agent’s plan, from identifying the root cause of a failing test to drafting and checking a fix.
  • Problems beyond coding: Mellum2.1 is a capable general assistant, too. It handles everyday questions and works through hard math and reasoning problems step by step.
  • Private, self-hosted deployment: Run Mellum2.1 locally or on your own infrastructure to keep code and data fully under your control.

Get started with Mellum2.1

Mellum2.1 is available on Hugging Face. GGUF builds for llama.cpp, Ollama, and LM Studio, as well as the multi-token prediction (MTP) head for speculative decoding in vLLM, are coming soon.

If you’re building coding agents, sub-agents, or AI tools that run on your own infrastructure, we’d love for you to try Mellum2.1. Tell us what works and what doesn’t. Your feedback will shape the next version.

Open source is how better models get made.

Try Mellum

Discover more

← All articles

What this article says

More in Software Development

All →
新登場!Kahoot! 360のCanva連携機能で、プロ仕様のインタラクティブなプレゼンテーションをシームレスに作成
Kahoot

新登場!Kahoot! 360のCanva連携機能で、プロ仕様のインタラクティブなプレゼンテーションをシームレスに作成

Transforme tes présentations Canva en cours interactifs et sessions d’étude sur Kahoot!
Kahoot

Transforme tes présentations Canva en cours interactifs et sessions d’étude sur Kahoot!

Canvaのプレゼンテーションを、Kahoot! のインタラクティブな授業や学習セッションに変換
Kahoot

Canvaのプレゼンテーションを、Kahoot! のインタラクティブな授業や学習セッションに変換

신규 기능! Kahoot! 360과 Canva의 통합으로 더욱 쉬워진 업무용 인터렉티브 프레젠테이션 제작
Kahoot

신규 기능! Kahoot! 360과 Canva의 통합으로 더욱 쉬워진 업무용 인터렉티브 프레젠테이션 제작

Canva 프레젠테이션을 Kahoot!에서 인터렉티브 수업과 학습 세션으로 변환하세요
Kahoot

Canva 프레젠테이션을 Kahoot!에서 인터렉티브 수업과 학습 세션으로 변환하세요

Novo! Crie apresentações interativas e profissionais com facilidade usando a integração do Kahoot! 360 com o Canva
Kahoot

Novo! Crie apresentações interativas e profissionais com facilidade usando a integração do Kahoot! 360 com o Canva

More from JetBrains

Vulkan Rendering Is Now The Default on Linux Wayland
JetBrains

Vulkan Rendering Is Now The Default on Linux Wayland

JetBrains Air in GoLand: Build, Review, and Profile Go Code With Agents
JetBrains

JetBrains Air in GoLand: Build, Review, and Profile Go Code With Agents

Security Update for YouTrack Server: Java Vulnerability CVE-2026-114938 (Java4Shell)
JetBrains

Security Update for YouTrack Server: Java Vulnerability CVE-2026-114938 (Java4Shell)

Top Version Control Tools: What the Data Shows
JetBrains

Top Version Control Tools: What the Data Shows

Under the Hood of Native WSL Mode in RubyMine: IJent and EelApi
JetBrains

Under the Hood of Native WSL Mode in RubyMine: IJent and EelApi

LinkedIn Connected Apps 1.2: Clearer Level System, Visible Progress, and Direct Answers About Privacy
JetBrains

LinkedIn Connected Apps 1.2: Clearer Level System, Visible Progress, and Direct Answers About Privacy