LaunchAI ModelsAI Agents
Jun 4, 1:02 PM
NVIDIA releases Nemotron 3 Ultra open model for long-running agents
Nemotron 3 Ultra is a 550B-parameter MoE model (55B active) built for long-running agents, offering 5x higher throughput and up to 30% lower token cost than similar open models. It uses a hybrid Mamba-2 MoE Transformer architecture and is available on Hugging Face.
·
Jun 4, 1:02 PM
