--- title: Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents description: JetBrains released Mellum2.1, an updated version of its 12B mixture-of-experts open model with 2.5B active parameters, released under Apache 2.0. The... canonical: https://daily.dev/posts/mellum2-1-gets-to-work-a-fast-open-model-for-coding-agents-cpbr6alyw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents | daily.dev og:description: JetBrains released Mellum2.1, an updated version of its 12B mixture-of-experts open model with 2.5B active parameters, released under Apache 2.0. The... og:url: https://daily.dev/posts/mellum2-1-gets-to-work-a-fast-open-model-for-coding-agents-cpbr6alyw og:image: https://api.daily.dev/og/posts/CpBR6ALyw.png og:image:alt: Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents **[JetBrains](https://daily.dev/sources/jetbrains)** · 3 min read · 0 upvotes · 0 comments ## Summary JetBrains released Mellum2.1, an updated version of its 12B mixture-of-experts open model with 2.5B active parameters, released under Apache 2.0. The architecture is unchanged from Mellum2, but the model underwent extensive reinforcement learning in real sandboxed environments, improving its ability to explore codebases, edit files, and verify its own changes. Benchmarks show gains in agentic coding, competitive programming, math, and tool calling versus Mellum2, Qwen3.5-9B, and Gemma 4 E4B, with multi-token prediction making it roughly 1.6x faster per request and the fastest under heavy load. It's aimed at powering coding agents and sub-agents that can be self-hosted, and is available now on Hugging Face with GGUF builds coming soon. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is new in JetBrains Mellum2.1 compared to Mellum2? Mellum2.1 keeps the same 12B mixture-of-experts architecture with 2.5B active parameters as Mellum2, but adds extensive post-training reinforcement learning across thousands of sandboxed environments. This lets it explore a codebase, edit files, and check its own changes, with the biggest gains showing up in agentic coding tasks compared to the original Mellum2. _Developers evaluating open coding-agent models can follow releases like this on daily.dev._ ### How fast is JetBrains Mellum2.1 compared to Qwen3.5-9B and Gemma 4 E4B? Mellum2.1 is the fastest of the group under heavy load, serving almost twice as many tokens as Qwen3.5-9B. For a single request, its multi-token prediction feature makes it about 1.6 times faster than without it, while the underlying architecture remains unchanged from Mellum2 so base speed is preserved. _Teams comparing self-hosted model throughput can track benchmarks like these on daily.dev._ ### Where can I download JetBrains Mellum2.1 and what license does it use? Mellum2.1 is available on Hugging Face under the Apache 2.0 license. GGUF builds for llama.cpp, Ollama, and LM Studio, plus a multi-token prediction head for speculative decoding in vLLM, are planned as follow-up releases for self-hosted deployment. _Anyone picking a license-friendly local model for agent infrastructure can keep tabs on updates via daily.dev._ ## Similar posts on daily.dev - [JetBrains open-sources Mellum2 to go where Claude Code can’t](https://daily.dev/posts/jetbrains-open-sources-mellum2-to-go-where-claude-code-can-t-hpsuvgcq0) · The New Stack · 21 upvotes · 7 comments - [Mellum2 Goes Open Source: A Fast Model for AI Workflows](https://daily.dev/posts/mellum2-goes-open-source-a-fast-model-for-ai-workflows-njuqs9a8q) · JetBrains · 4 upvotes · 0 comments - [Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains](https://daily.dev/posts/introducing-mellum2-a-12b-mixture-of-experts-model-by-jetbrains-ztgyhiwra) · Hugging Face · 3 upvotes · 0 comments --- Tags: [#open-source](https://daily.dev/tags/open-source), [#ai-agents](https://daily.dev/tags/ai-agents), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#jetbrains](https://daily.dev/tags/jetbrains) [View this post on daily.dev](https://daily.dev/posts/mellum2-1-gets-to-work-a-fast-open-model-for-coding-agents-cpbr6alyw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents","url":"https://daily.dev/posts/mellum2-1-gets-to-work-a-fast-open-model-for-coding-agents-cpbr6alyw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/mellum2-1-gets-to-work-a-fast-open-model-for-coding-agents-cpbr6alyw"},"datePublished":"2026-10-08T12:19:58.920Z","dateModified":"2026-10-08T14:18:05.791Z","description":"JetBrains released Mellum2.1, an updated version of its 12B mixture-of-experts open model with 2.5B active parameters, released under Apache 2.0. The...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/50b9483d51ba3ab6ecac6871e3c0979d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/50b9483d51ba3ab6ecac6871e3c0979d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"JetBrains","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"JetBrains","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/53ecf0c676f34b3896ee109609d91efa","url":"https://daily.dev/sources/jetbrains"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/mellum2-1-gets-to-work-a-fast-open-model-for-coding-agents-cpbr6alyw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"open-source,ai-agents,reinforcement-learning,jetbrains","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"JetBrains","item":"https://daily.dev/sources/jetbrains"},{"@type":"ListItem","position":3,"name":"Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/mellum2-1-gets-to-work-a-fast-open-model-for-coding-agents-cpbr6alyw#faq","mainEntity":[{"@type":"Question","name":"What is new in JetBrains Mellum2.1 compared to Mellum2?","acceptedAnswer":{"@type":"Answer","text":"Mellum2.1 keeps the same 12B mixture-of-experts architecture with 2.5B active parameters as Mellum2, but adds extensive post-training reinforcement learning across thousands of sandboxed environments. This lets it explore a codebase, edit files, and check its own changes, with the biggest gains showing up in agentic coding tasks compared to the original Mellum2. Developers evaluating open coding-agent models can follow releases like this on daily.dev."}},{"@type":"Question","name":"How fast is JetBrains Mellum2.1 compared to Qwen3.5-9B and Gemma 4 E4B?","acceptedAnswer":{"@type":"Answer","text":"Mellum2.1 is the fastest of the group under heavy load, serving almost twice as many tokens as Qwen3.5-9B. For a single request, its multi-token prediction feature makes it about 1.6 times faster than without it, while the underlying architecture remains unchanged from Mellum2 so base speed is preserved. Teams comparing self-hosted model throughput can track benchmarks like these on daily.dev."}},{"@type":"Question","name":"Where can I download JetBrains Mellum2.1 and what license does it use?","acceptedAnswer":{"@type":"Answer","text":"Mellum2.1 is available on Hugging Face under the Apache 2.0 license. GGUF builds for llama.cpp, Ollama, and LM Studio, plus a multi-token prediction head for speculative decoding in vLLM, are planned as follow-up releases for self-hosted deployment. Anyone picking a license-friendly local model for agent infrastructure can keep tabs on updates via daily.dev."}}]} ```