NVIDIA Nemotron 3 Ultra now available on Amazon SageMaker JumpStart
NVIDIA's open Nemotron 3 Ultra model launches day-zero on Amazon SageMaker JumpStart for agentic workloads.
“Nemotron 3 Ultra is an open model built for frontier reasoning and orchestration in long-running autonomous agents, delivering 5x faster inference and up to 30% lower cost for agentic workloads.”
NVIDIA's open Nemotron 3 Ultra, a 550B-parameter (55B active) hybrid Transformer-Mamba MoE model optimized for NVFP4, is now available with one-click deployment on Amazon SageMaker JumpStart. It targets long-running autonomous agents with 5x faster inference, up to 30% lower cost, and 1M-token context, signaling the continued push toward purpose-built models for sustained multi-step agentic reasoning.