NVIDIA Nemotron 3.5 Super VL is now available in Amazon SageMaker JumpStart

What happened

NVIDIA Nemotron 3.5 Super VL, a 120B-parameter multimodal (able to work with more than one kind of input, such as text and images) vision-language model, is now available in Amazon SageMaker JumpStart. You can deploy it with a few steps in SageMaker Studio or with a few lines of the SageMaker Python SDK (the toolkit a developer builds on a platform with). NVIDIA is a semiconductor company based in Santa Clara.

Super VL is the vision-language model (VLM) in the NVIDIA Nemotron 3.5 family. It accepts images, video, and text as input and generates text.

The model pairs a 120B-parameter hybrid Mixture-of-Experts (MoE) language backbone with 12B active parameters and a C-RADIO vision encoder. It provides support for context lengths of up to 1 million tokens and includes a built-in Multi-Token Prediction (MTP) head that supports speculative decoding.

NVIDIA built Super VL for document intelligence, GUI understanding for computer-use agents, video question answering, and multimodal agentic (AI that carries out multi-step tasks rather than answering one question) applications. JumpStart offers two variants: NVFP4, quantized from BF16 with quantization-aware distillation for optimized inference, and the BF16 full-precision reference weights.

Model overview Nemotron 3.5 Super VL is a 120B-parameter model with 12B active parameters per token. It combines a hybrid language backbone with a dedicated vision encoder.

Language backbone : 88 layers that interleave Mamba-2 and MoE layers (512 routed experts, 22 active per token) with 8 attention layers, plus a shared MTP head. The backbone is initialized from Nemotron 3 Super Base and distilled from Nemotron 3 Ultra Base.