Amazon Web Services announced the availability of NVIDIA Nemotron 3.5 Super VL on Amazon SageMaker JumpStart. This vision-language model (VLM) can process images, video, and text to generate text. It is designed for tasks like document intelligence, GUI understanding, video question answering, and multimodal agentic applications.
What happened
Amazon Web Services (AWS) has announced the availability of NVIDIA Nemotron 3.5 Super VL on Amazon SageMaker JumpStart. This vision-language model (VLM) can process images, video, and text to generate text, making it suitable for tasks such as document intelligence, GUI understanding, video question answering, and multimodal agentic applications. The model is available in two variants: NVFP4, optimized for inference on G7 instances, and BF16, available on ml.p5en.48xlarge instances. Users can deploy the model through SageMaker Studio or the SageMaker Python SDK.
What to weigh
- Service quota for ml.g7.24xlarge, ml.g7.48xlarge, or ml.p5en.48xlarge endpoint usage is required.
- Choose NVFP4 for optimized inference or BF16 for full-precision reference weights.
Source: Amazon Web Services
