Accelerate agentic AI with NVIDIA Nemotron models on Amazon EKS and SageMaker HyperPod EKS
NVIDIA's open multimodal MoE model joins the Nemotron family on AWS
Availability change
NVIDIA Nemotron 3.5 Super VL is now available on AWS, joining the Nemotron 3 Nano, Nano Omni, Super, Ultra and Nemotron 3.5 Lightning models already offered there.
It is a 120B-parameter mixture-of-experts model that activates 12B parameters per token and combines reasoning and tool use with text, image, document and video understanding, so one model serves both text and visual tasks.
NVIDIA publishes the weights, training datasets and post-training recipes, letting teams customize the model for domain-specific workloads and run it on infrastructure they control.
The model takes text, image, document and video input and returns text, supports context lengths up to 1M tokens, and ships in BF16 and NVFP4 checkpoints.
NVIDIA reports 63.44 percent on Hermes Bench, 87.05 percent on LangChain agent evaluations and 80.8 percent on the CharXiv chart-reasoning benchmark.
A reference implementation runs on Amazon EKS, EKS Auto Mode and SageMaker HyperPod EKS, validated on p6-b200.48xlarge and p5en.48xlarge instances, with a walkthrough in the aws-do-eks project.
NVIDIA Nemotron 3.5 Super VL joins the NVIDIA Nemotron 3 Nano , Nano Omni , Super , Ultra , and Nemotron 3.5 Lightning models already available on AWS. It’s a 120B-parameter mixture-of-experts (MoE) model that activates 12B parameters per token.
It combines reasoning and tool use with text, image, document, and video understanding, so one model serves both text and visual tasks. This post explores its architecture and use cases, then shows how to deploy it on Amazon Elastic Kubernetes Service (Amazon EKS) , Amazon EKS Auto Mode , and Amazon SageMaker HyperPod EKS .
About Nemotron 3.5 Super VL
NVIDIA Nemotron 3.5 Super VL is an open multimodal model distilled from Nemotron 3 Ultra. NVIDIA publishes the weights, training datasets, and post-training recipes, so you can customize the model for domain-specific workloads and run it on infrastructure you control. Model details:
120B total parameters, 12B active per token.
Hybrid Mamba-2, MoE , and attention layers with a RADIO vision encoder.
Amazon EKS, EKS Auto Mode and SageMaker HyperPod EKS, validated on p6-b200.48xlarge and p5en.48xlarge instances, with a walkthrough in the aws-do-eks project.
aws.amazon.com