NEWS · MODELS · #3311
NVIDIA Nemotron 3.5 Super VL available in Amazon SageMaker JumpStart
NVIDIA's Nemotron 3.5 Super VL — a 120B-parameter hybrid MoE vision-language model (12B active parameters) with a C-RADIO vision encoder, 1M-token context support, and an MTP head — is now available in Amazon SageMaker JumpStart. JumpStart offers a quantized NVFP4 variant optimized for inference and a BF16 full-precision reference; the BF16 weights can be downloaded for customization, and the service shows measured inference performance and deployment options on AWS instances.
KEY POINTS
- NVIDIA's Nemotron 3.5 Super VL — a 120B-parameter hybrid MoE vision-language model (12B active parameters) with a C-RADIO vision encoder, 1M-token context support, and an MTP head — is now available in Amazon SageMaker JumpStart.
- JumpStart offers a quantized NVFP4 variant optimized for inference and a BF16 full-precision reference; the BF16 weights can be downloaded for customization, and the service shows measured inference performance and deployment options on AWS instances.
- Makes a large, long-context multimodal VLM (with a quantized low-cost inference option) directly usable on AWS, lowering barriers for building vision-language agents, document and video understanding, and multimodal agent workflows.
WHY IT MATTERS
Makes a large, long-context multimodal VLM (with a quantized low-cost inference option) directly usable on AWS, lowering barriers for building vision-language agents, document and video understanding, and multimodal agent workflows.