Uploaded October 2026 | Updated November 2026, 4 days ago
Learn how NVIDIA Nemotron 3.5 Super VL investigates why an AI bill rose 30% using a dashboard screenshot and a scanned pricing sheet.
In this walkthrough, Chris Alexiuk introduces the open 120-billion-parameter mixture-of-experts model with 12 billion active parameters, then Chia-Chih Chen demonstrates a visual investigation agent. The agent reads the dashboard, identifies a surge in thinking-token use, writes Python to compare routing options and prepares a proposal for human approval. The recommended plan stays within the teamβs quality bar while projecting about $100,000 in monthly savings.
NVIDIA Nemotron 3.5 Super VL combines multimodal reasoning, tool use and code generation for agents that work across text, images, charts, documents and video. It can also run on a single NVIDIA DGX Spark.
Use the links and chapters below to explore the model, technical blog and developer resources.
β‘οΈ Learn more: blogs.nvidia.com/blog/nemotron-3-5-super-vl
π Technical blog: developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning
π₯ Download the model: huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16
π Try on NVIDIA Build: build.nvidia.com/nvidia/nemotron-3.5-super-vl-120b-a12b
π Super VL cookbook: github.com/NVIDIA-NeMo/Nemotron/tree/main/usage-cookbook/Nemotron-3.5-Super-VL/visual-investigation-agent
π Technical report: research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3.5-Super-and-Lightning-Technical-Report.pdf
Chapters:
00:00 β Introduction
00:07 β NVIDIA Nemotron 3.5 Super VL overview
00:31 β Vision-language capabilities
01:09 β Multimodal billing investigation demo
01:46 β Read dashboard metrics
01:54 β Parse a scanned pricing sheet
02:01 β Find the cause of the cost increase
02:09 β Optimize ticket routing with Python
02:16 β Prepare a proposal for human review
02:28 β Cookbook and developer resources
Learn how NVIDIA Nemotron 3.5 Super VL investigates why an AI bill rose 30% using a dashboard screenshot and a scanned pricing sheet.
In this walkthrough, Chris Alexiuk introduces the open 120-billion-parameter mixture-of-experts model with 12 billion active parameters, then Chia-Chih Chen demonstrates a visual investigation agent. The agent reads the dashboard, identifies a surge in thinking-token use, writes Python to compare routing options and prepares a proposal for human approval. The recommended plan stays within the teamβs quality bar while projecting about $100,000 in monthly savings.
NVIDIA Nemotron 3.5 Super VL combines multimodal reasoning, tool use and code generation for agents that work across text, images, charts, documents and video. It can also run on a single NVIDIA DGX Spark.
Use the links and chapters below to explore the model, technical blog and developer resources.
β‘οΈ Learn more: blogs.nvidia.com/blog/nemotron-3-5-super-vl
π Technical blog: developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning
π₯ Download the model: huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16
π Try on NVIDIA Build: build.nvidia.com/nvidia/nemotron-3.5-super-vl-120b-a12b
π Super VL cookbook: github.com/NVIDIA-NeMo/Nemotron/tree/main/usage-cookbook/Nemotron-3.5-Super-VL/visual-investigation-agent
π Technical report: research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3.5-Super-and-Lightning-Technical-Report.pdf
Chapters:
00:00 β Introduction
00:07 β NVIDIA Nemotron 3.5 Super VL overview
00:31 β Vision-language capabilities
01:09 β Multimodal billing investigation demo
01:46 β Read dashboard metrics
01:54 β Parse a scanned pricing sheet
02:01 β Find the cause of the cost increase
02:09 β Optimize ticket routing with Python
02:16 β Prepare a proposal for human review
02:28 β Cookbook and developer resources










