NVIDIA Nemotron 3.5 Lightning model is now available on Amazon SageMaker JumpStart

NVIDIA Nemotron 3.5 Lightning on Amazon SageMaker JumpStart

AWS customers now have access to the fastest open model in its class for persistent agent workloads and rapid task execution with the availability of NVIDIA's Nemotron 3.5 Lightning on Amazon SageMaker JumpStart.

This model is engineered for persistent agents and high-throughput enterprise automation across various domains including personal assistants, financial document processing, cybersecurity triage, and telecom operations. Built on a hybrid Mixture-of-Experts (MoE) architecture, it boasts 30B total parameters with 3B active per forward pass, achieving up to 4x the throughput (~410 tokens/sec) and 30% faster task completion compared to similar models.

• Key Features: Handles up to 1M tokens of context via DFlash speculative decoding, integrates with popular agent harnesses, and is fully open-trained on open datasets.
• Deployment: Deployable in a few clicks through the SageMaker JumpStart model catalog in the SageMaker console or using the SageMaker Python SDK.

What to do

• Navigate to the SageMaker JumpStart model catalog in the SageMaker console.
• Use the SageMaker Python SDK to deploy the models to your AWS account.
• Refer to the Amazon SageMaker JumpStart documentation for more information on deploying and using foundation models.

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.