A Blog post by JetBrains on Hugging Face
Back to Articles
Mellum2 is a 12B-parameter Mixture-of-Experts model trained from scratch on natural language and code.
The model activates only 2.5B parameters per token, making it efficient for high-throughput, low-latency inference.
Mellum2 is can be used for routing, RAG, summarization, sub-agents, high-throughput coding features, and private deployments.
It is released under the Apache 2.0 license.
JetBrains Releases Mellum2: A 12B MoE Model for Fast, Specialized Tasks in Multi-Model AI Pipelines
JetBrains open-sources Mellum 2, featuring 12B total parameters
Mellum2 Goes Open Source: A Fast Model for AI Workflows | The JetBrains AI Blog
JetBrains open-sources Mellum2 to challenge third-party API limitations
Cheaper, Better, Faster, Stronger | Mistral AI
Olmix: A framework for data mixing throughout LM development | Ai2
Running Mixtral 8x7B at 21+ TPS on Pure CPU via io_uring and Predictive Caching
NVIDIA AI Releases Nemotron 3 Ultra: An Open 550B Mixture-of-Experts Hybrid Mamba-Transformer for Long-Running Agents
Mistral Small 3 | Mistral AI
MiniMax M3 debuts, eclipsing GPT-5.5 and Gemini 3.1 Pro on key benchmark performance for just 5-10% of the cost
JetBrains open-sources Mellum2, a 12B MoE model with 2.5B active parameters for routing, RAG, and sub-agent pipelines.
JetBrains has open-sourced Mellum 2, the successor to Mellum, its code completion-focused model that was also released as open…
Trained from scratch and designed for practical deployment, Mellum2 is built for routing, Q&A, sub-agents, and private AI use in…
JetBrains open-sources Mellum2, a fast, 12B-parameter coding model running on your own infrastructure, surpassing limitations of…
Researchers at the Allen Institute for AI and UC Berkeley have built EMO, a mixture-of-experts model whose experts specialize in…
A Blog post by Ai2 on Hugging Face
