NVIDIA Nemotron 3.5 Super VL arrives in SageMaker JumpStart
AWS announced that NVIDIA Nemotron 3.5 Super VL is available through Amazon SageMaker JumpStart and can be deployed with SageMaker Studio or the SageMaker Python SDK. The vision-language model accepts images, video, and text; JumpStart offers NVFP4 weights for optimized inference and BF16 reference weights, while NVIDIA says the model has a 120B-parameter backbone, 12B active parameters, and support for contexts up to one million tokens.
The release gives AWS users managed access to a large multimodal model for document intelligence, GUI understanding, video question answering, and multimodal agentic applications, with both optimized-inference and customization-oriented checkpoints.
Today, we’re announcing that NVIDIA Nemotron 3.5 Super VL is available in Amazon SageMaker JumpStart. You can deploy it with a few steps in SageMaker Studio or with a few lines of the SageMaker Python SDK. Super VL is the vision-language model (VLM) in the NVIDIA Nemotron 3.5 family. It accepts images, video, and text as input and generates text.
The model pairs a 120B-parameter hybrid Mixture-of-Experts (MoE) language backbone with 12B active parameters and a C-RADIO vision encoder. It supports context lengths of up to 1 million tokens and includes a built-in Multi-Token Prediction (MTP) head that supports speculative decoding. You can configure reasoning per request.
NVIDIA built Super VL for document intelligence, GUI understanding for computer-use agents, video question answering, and multimodal agentic applications. JumpStart offers two variants: NVFP4, quantized from BF16 with quantization-aware distillation for optimized inference, and the BF16 full-precision reference weights. In this post, we walk through the model’s capabilities and the JumpStart deployment configurations. We then show the measured inference performance and demonstrate text, image, and video inference.
Model overview
Nemotron 3.5 Super VL is a 120B-parameter model with 12B active parameters per token. It combines a hybrid language backbone with a dedicated vision encoder.
#NVIDIA#NVIDIA Nemotron 3.5 Super VL#Amazon SageMaker JumpStart#Amazon SageMaker Studio#SageMaker Python SDK#C-RADIO#NVIDIA NeMo RL#NVIDIA NeMo Gym#NVIDIA Model Optimizer