NVIDIA Nemotron 3 Ultra now available on Amazon SageMaker JumpStart

This article announces the day-zero availability of NVIDIA Nemotron 3 Ultra on Amazon SageMaker JumpStart, a new open language model optimized for agentic AI workloads.

• 550B total parameters with 55B active parameters using hybrid Transformer-Mamba MoE architecture
• 5x faster inference and up to 30% lower cost for agentic workloads
• Supports up to 1M token context length for long-running autonomous agents
• One-click deployment through SageMaker JumpStart with no infrastructure management required
• Ideal for agent orchestrators, coding agents, deep research, and complex enterprise workflows
• Requires GPU instances like ml.p5en.48xlarge with associated hourly costs

Nemotron 3 Ultra enables efficient multi-step reasoning for production agents by activating only necessary parameters, maintaining coherence across hundreds of turns while managing costs effectively.