NVIDIA Nemotron 3.5 Super VL Now Available on Amazon EKS and SageMaker HyperPod

1 reports archived1 independent sourcesupdated 10/30/2026, 00:11:08

Synthesis & Latest Updates

1 Sources Cross-Validated

NVIDIA has released the 120B-parameter MoE model Nemotron 3.5 Super VL, now deployable on Amazon EKS and SageMaker HyperPod. Activating only 12B parameters per token, it unifies text, image, and video understanding to accelerate agentic AI development.

LATEST/NVIDIA has released the 120B-parameter MoE model Nemotron 3.5 Super VL, now deployable on Amazon EKS and SageMaker HyperPod. Activating only 12B parameters per token, it unifies text, image, and video understanding to accelerate agentic AI development.

Hourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first

AWS Machine Learning BlogT1Oct 30, 00:11·68 pts
NVIDIA Nemotron 3.5 Super VL Now Available on Amazon EKS and SageMaker HyperPod
- Nemotron 3.5 Super VL is a 120B-parameter Mixture-of-Experts (MoE) model that activates only 12B parameters per inference to balance performance and efficiency.
- The model features native multimodal capabilities, supporting text reasoning, tool use, and understanding of images, documents, and videos within a single architecture.
- Users can deploy via Amazon EKS or SageMaker HyperPod for Kubernetes-native orchestration, optimizing infrastructure costs for large-scale agentic workloads.
View Related Reports & Analysis Original Source