# NVIDIA Nemotron 3.5 Super VL becomes available on AWS

_Published Thursday, October 29, 2026 at 12:21 PM EDT · AI, Infrastructure · Latest · Tier 2 — Notable_

![NVIDIA Nemotron 3.5 Super VL becomes available on AWS — Primary](https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/28/ML-21105-featured-image.png)

NVIDIA's Nemotron 3.5 Super VL is available on AWS, AWS said, adding a model that combines reasoning and tool use with understanding of text, images, documents and video. It accepts up to 1M tokens of context and produces text output.

NVIDIA publishes the model weights, training datasets and post-training recipes for customization. AWS provides a reference implementation for deployment on Amazon EKS, EKS Auto Mode and SageMaker HyperPod EKS, with architecture validated on instances containing eight B200 or eight H200 GPUs.

The model activates 12B of its 120B parameters per token, reducing computation relative to using all parameters, but GPU memory must still hold the full weights.

## Sources

- [Artificial Intelligence](https://aws.amazon.com/blogs/machine-learning/accelerate-agentic-ai-with-nvidia-nemotron-models-on-amazon-eks-and-sagemaker-hyperpod-eks/)

---
Canonical: https://techandbusiness.org/newswire/fbTRcw1VPoFqLsL4a7wMgJ
Published: 2026-10-29T16:21:36.999Z
Story chronology: 2026-10-29T16:11:08.000Z
Retrieved: 2026-10-29T18:45:27.669Z
Publisher: Tech & Business (techandbusiness.org)