Accelerate agentic AI with NVIDIA Nemotron models on Amazon EKS and SageMaker HyperPod EKS
NVIDIA Nemotron 3.5 Super VL, a 120B MoE multimodal model, is now available on AWS
NVIDIA's Nemotron 3.5 Super VL, a 120B-parameter mixture-of-experts open multimodal model, is now deployable on Amazon EKS and SageMaker HyperPod EKS. The model activates only 12B parameters per token and supports text, image, document, and video inputs with a 1M token context window, making it efficient for agentic workflows. NVIDIA publishes weights and training recipes, enabling enterprise customization on self-managed infrastructure.