Loading market data...

JetBrains Releases Mellum2: A 12B MoE Model for Fast, Specialized Tasks in Multi-Model AI Pipelines

MarkTechPostJune 2, 2026 at 8:00 AM

JetBrains releases Mellum2 under Apache 2. 0 — a 12B MoE model trained on 10. 6 trillion tokens for AI workflows. The post JetBrains Releases Mellum2: A 12B MoE Model for Fast, Specialized Tasks in Multi-Model AI Pipelines appeared first on MarkTechPost.

This is a summary. For the full story, read the original article at MarkTechPost.

Original source: MarkTechPost

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

HuggingFaceJune 1, 2026 at 3:45 PM

OpenAI frontier models and Codex are now available on AWS

OpenAIJune 1, 2026 at 10:00 AM

Why Financial Institutions Are Converging on Transaction Foundation Models to Build Their Own Intelligence

NVIDIA BlogJune 2, 2026 at 6:00 AM

← Back to all articles

Related Articles

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

OpenAI frontier models and Codex are now available on AWS

Why Financial Institutions Are Converging on Transaction Foundation Models to Build Their Own Intelligence