AWS Adds NVIDIA Nemotron 3.5 Super VL to SageMaker JumpStart

AWS Machine Learning says NVIDIA Nemotron 3.5 Super VL is now available in Amazon SageMaker JumpStart. Users can deploy it from SageMaker Studio or with the SageMaker Python SDK. The vision-language model accepts images, video, and text, generates text, supports up to 1 million tokens of context, and includes an MTP head for speculative decoding. JumpStart offers NVFP4 for optimized inference and BF16 reference weights; NVFP4 runs on G7 instances with RTX PRO 4500 Blackwell GPUs, while BF16 is available on ml.p5en.48xlarge with H200 GPUs.