Nemotron 3.5 Super VL model now available on Amazon SageMaker JumpStart

NVIDIA’s Nemotron 3.5 Super VL has been added to Amazon SageMaker JumpStart, broadening the range of foundation models available to AWS users. This model processes images, video, and text as input and produces text output, enabling the deployment of multimodal AI solutions directly on AWS infrastructure. It is positioned for applications such as document intelligence, GUI understanding, video question answering, and multimodal agent workflows.

The model integrates a 120B-parameter hybrid Mixture-of-Experts language backbone with 12B active parameters and a vision encoder, supporting context lengths up to 1 million tokens. It features a built-in Multi-Token Prediction head for speculative decoding to speed up text generation, with reasoning adjustable per request. The model supports ten languages, including English, French, Spanish, German, Japanese, Hindi, Korean, and Chinese.

Post-training includes multimodal supervised fine-tuning on diverse data types such as images, videos, documents, charts, and GUIs, followed by GRPO reinforcement learning. It delivers structured JSON output, tool calling, and configurable reasoning tailored for enterprise agent workflows, enhancing its utility in production environments.

SageMaker JumpStart provides two deployment options: NVFP4 for optimized inference on G7 instances with NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, and BF16 reference weights on ml.p5en.48xlarge for customization including supervised fine-tuning, reinforcement learning, distillation, and domain adaptation. Customers can deploy the model with minimal setup through the SageMaker JumpStart model catalog or the SageMaker Python SDK.