Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains

This article presents Mellum2, a 12B-parameter Mixture-of-Experts model by JetBrains designed for efficient code and natural language processing.

• •The model activates only 2.5B parameters per token, enabling more than 2x faster inference compared to similarly-sized models
• •It is optimized for multiple AI system workloads including routing, RAG pipelines, summarization, sub-agents, and private deployments
• •Mellum2 specializes in text and code tasks rather than multimodal capabilities, maintaining efficiency for software engineering use cases
• •The model is released as open-source under Apache 2.0 license and available on Hugging Face

This summary was automatically generated by AI based on the original article and may not be fully accurate.