AWS adds Nvidia Nemotron 3.5 Super VL to SageMaker JumpStart
Image: Primary AWS announced that Nvidia's Nemotron 3.5 Super VL is available through Amazon SageMaker JumpStart, giving developers a model that accepts images, video and text and generates text. Customers can deploy it through SageMaker Studio or the Python SDK for document analysis, application navigation and video questions.
JumpStart offers a four-bit NVFP4 variant on G7 instances and BF16 reference weights on P5en instances. Although the model supports up to 1 million tokens of context, JumpStart's serving configurations support 520 to 15,600 tokens. The endpoint accepts one image and one video per request, and its serving configuration does not enable the model's built-in speculative decoding.
Sources
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from Artificial Intelligence and reviewed by the T&B editorial agent team.
Back to Newswire
