NVIDIA Released 'Nemotron 3.5 Super VL', Which Powers Persistent, Multimodal Agents

IBL News | New York

NVIDIA released Nemotron 3.5 Super VL, a 120-billion-parameter open-source model that the company said can work across PDFs, charts, tables, images, and webpages while following instructions and using tools.

It’s a customizable multimodal system for specialized workflows, with a 120B-parameter mixture-of-experts (MoE) architecture that activates 12B parameters per token, balancing model capacity with inference efficiency.

It comes with always-on agents designed for taking on longer, more complex enterprise workflows.

The model combines reasoning, instruction following, and tool use with text, image, document, and video understanding.

• Coding: Test and validate code, analyze errors, and recommend fixes.
• Web research: Search across websites, connect information, and verify answers.
• Document intelligence: Extract information from tables, charts, and page layouts to produce summaries and reports.
• Cybersecurity: Identify security vulnerabilities and triage threats to prioritize remediation.
• Video understanding: Extract information for search, content review, and incident analysis.

By combining these capabilities into a single model, teams can handle text and visual tasks without deploying separate text and vision-language models or passing task context between them.

For example, a single request can involve reading a document, checking information across sources, following company policy, and calling several tools.

Another example, before producing a useful answer, can be reviewing a credit agreement to extract figures from tables, interpret a chart, check a related webpage, and apply the company’s own rules.

On a single GPU, this model delivers up to 5x higher throughput for agentic tasks compared to other open models in its size category.

Developers can post-train Nemotron 3.5 Super VL with NVIDIA NeMo using their own data, tools, policies, and workflows.

This model was also optimized to run locally on NVIDIA DGX Spark.

Several NVIDIA partners supported customization and deployment of Nemotron 3.5 Super VL for domain-specific workflows.

• AfterQuery
• AgileRL
• AI21
• Alice
• Applied Compute
• Baseten
• Bespoke Labs
• Databricks
• distil labs
• Fastino Labs
• Fireworks AI
• Handshake
• Mercor
• Mindbeam
• ms-swift
• Multiverse Computing
• Prime Intellect
• Reasonable
• River AI
• Scale AI
• Thinking Machines Lab (Tinker)
• TNG
• Trajectory