JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents

MarkTechPostPublished 17 days ago

JetBrains launched Mellum2.1, a 12-billion-parameter mixture-of-experts model optimized for coding agents, activating 2.5B parameters per token. It improves over Mellum2 mainly via reinforcement learning in real software environments, excelling in coding benchmarks and supporting long contexts.

#hugging-face #jetbrains #mellum2-1 #nvidia-h200 #reinforcement-learning #software-engineering

JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents

More in Machine Learning

PyTorch Conference 2026: Google and Meta Open-Source TorchTPU for Native PyTorch on TPUs

Hugging Face Releases Carbon-X, a 14B Open DNA Language Model that Brings DNA and Natural Language Together for the First Time

Google ML Drift Accelerates On-Device AI Inference Across Diverse GPUs