Nemotron 3.5 Super VL model now available on Amazon SageMaker JumpStart

NVIDIA Nemotron 3.5 Super VL on SageMaker JumpStart

NVIDIA's Nemotron 3.5 Super VL is now available on Amazon SageMaker JumpStart, enabling customers to deploy multimodal AI solutions on AWS infrastructure. This vision-language model supports images, video, and text inputs, generating text for applications like document intelligence, GUI understanding, and video question answering.

Key Features

• 120B-parameter hybrid MoE language backbone with 12B active parameters
• Vision encoder supporting context lengths up to 1 million tokens
• Built-in MTP head for speculative decoding to accelerate text generation
• Multimodal supervised fine-tuning on various data types
• Support for ten languages including English, French, Spanish, and more
• Structured JSON output, tool calling, and configurable reasoning

Deployment

Deploy Nemotron 3.5 Super VL with just a few clicks via the SageMaker JumpStart model catalog in the SageMaker console or using the SageMaker Python SDK. Two variants are available: NVFP4 for optimized inference on G7 instances and BF16 reference weights on ml.p5en.48xlarge for customization.

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

Source: AWS release notes

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.