NVIDIA Nemotron 3.5 Lightning now available in Amazon SageMaker JumpStart
NVIDIA's Nemotron 3.5 Lightning now runs on SageMaker JumpStart—4x throughput gains for always-on agents, no custom infrastructure needed.
Why it matters
A production-ready open model for agentic workloads is now integrated into AWS's managed ML platform, lowering the barrier for practitioners deploying agent fleets at scale.
The key facts
11 to knowNVIDIA Nemotron 3.5 Lightning: 30B MoE model (3B active parameters)
4x higher throughput vs baseline
30% faster task completion for always-on agents
Available in Amazon SageMaker JumpStart (managed deployment)
Optimized for high-volume agentic workloads
Open model (weights available)
Nemotron 3.5 Lightning: 30B MoE (3B active parameters)
4x higher throughput vs. baseline
Available in Amazon SageMaker JumpStart
Open model, optimized for high-volume agentic workloads
Published August 17, 2026
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: NVIDIA Nemotron 3.5 Lightning, an open model built for high-volume agentic workloads, is now available in Amazon SageMaker JumpStart. This post shows how to deploy the 30B Mixture-of-Experts model (3B active), which delivers up to 4x higher throughput and up to 30% faster task completion for…