Nemotron 3.5 Super VL: an open model that reads documents, images and video
On October 15, 2026, NVIDIA released Nemotron 3.5 Super VL, with 120B parameters and 12B active, open weights, data and recipes, text, image and video input and up to 1 million tokens of context.
Source: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt Models (blogs.nvidia.com). Text prepared with AI from this source.
What happened and what to do
According to the model page, the full-precision version runs on 4 H100 or 2 GB200, and there is also an NVFP4 quantized version. The license is OpenMDW-1.1. NVIDIA says the model was trained on about 26 trillion tokens and targets specialized agents, document and video understanding, without audio support.
For companies with many PDFs, forms, charts or videos, an open model of this size can run on their own infrastructure. It is worth measuring quality on real documents and the GPU cost before deciding.
How the consultancy can help
Wendelmaques can set up, on demand, a test of Nemotron 3.5 Super VL with your documents, compare it with your current solution and, if it pays off, put the model into production with monitoring.
Next step
If your team processes documents or video at volume, send a short description of the case and receive a scoped proposal.
Let's assess your project
I reply with scope and a proposal.