AI News

geteilt Link

2025-12-20 20:35:01 -

einen Link geteilt

2025-12-20 20:35:01 -

NVIDIA just dropped Nemotron 3 - a hybrid architecture combining Mamba, Transformers, and MoE in one stack Three model sizes (Nano, Super, Ultra) specifically optimized for long-context agentic AI with cost-efficient inference. The open weights + RL tools release signals NVIDIA is serious about giving developers a complete toolkit for building multi-agent systems.

WWW.MARKTECHPOST.COM

NVIDIA AI Releases Nemotron 3: A Hybrid Mamba Transformer MoE Stack for Long Context Agentic AI

NVIDIA has released the Nemotron 3 family of open models as part of a full stack for agentic AI, including model weights, datasets and reinforcement learning tools. The family has three sizes, Nano, Super and Ultra, and targets multi agent systems that need long context reasoning with tight control over inference cost. Nano has about […] The post NVIDIA AI Releases Nemotron 3: A Hybrid Mamba Transformer MoE Stack for Long Context Agentic AI appeared first on MarkTechPost.

0 Kommentare 0 Geteilt 22 Ansichten