GUIDE · MODELS · #2791
NVIDIA publishes Nemotron 3.5 Super VL (120B MoE) and provides AWS EKS / SageMaker deployment guide
NVIDIA released Nemotron 3.5 Super VL, an open multimodal 120B-parameter mixture-of-experts (MoE) model that activates about 12B parameters per token and is distilled from Nemotron 3 Ultra. NVIDIA published the model weights, training datasets, and post-training recipes and published reference implementations and an aws-do-eks walkthrough showing how to deploy Nemotron models on Amazon EKS, EKS Auto Mode, and SageMaker HyperPod EKS; the model is validated on AWS GPU instances and integrates with major agent frameworks via the NVIDIA Agent Toolkit.
KEY POINTS
- NVIDIA released Nemotron 3.5 Super VL, an open multimodal 120B-parameter mixture-of-experts (MoE) model that activates about 12B parameters per token and is distilled from Nemotron 3 Ultra.
- NVIDIA published the model weights, training datasets, and post-training recipes and published reference implementations and an aws-do-eks walkthrough showing how to deploy Nemotron models on Amazon EKS, EKS Auto Mode, and SageMaker HyperPod EKS; the model is validated on AWS GPU instances and integrates with major agent frameworks via the NVIDIA Agent Toolkit.
- Open weights, datasets, and deployment recipes plus validated AWS orchestration examples make it easier for organizations to run and customize a large multimodal agent-capable model on their own cloud or infrastructure.
WHY IT MATTERS
Open weights, datasets, and deployment recipes plus validated AWS orchestration examples make it easier for organizations to run and customize a large multimodal agent-capable model on their own cloud or infrastructure.