# NVIDIA releases a 120B open multimodal model for AI agents

> Source: <https://runtimewire.com/article/nvidia-nemotron-35-super-vl-open-multimodal-agents>
> Published: 2026-10-15 16:20:39+00:00

# NVIDIA releases a 120B open multimodal model for AI agents

**Nemotron 3.5 Super VL combines text, image, document and video processing; NVIDIA says it completed 10,000 coding tasks up to four times faster in its tests.**

        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)
        · Published 

Primary source: [X](https://x.com/nvidiaai/status/2110749836450713896?s=46)

## Why it matters

NVIDIA is pairing an open multimodal model with datasets and customization recipes, giving companies a way to adapt agent software to private workflows while keeping NVIDIA's compute and deployment stack in the picture.

[NVIDIA](https://www.nvidia.com/) released [Nemotron 3.5 Super VL](https://runtimewire.com/models/nvidia/nemotron-3.5-super-vl:free) on October 15th, an open multimodal model designed for AI agents that need to reason, use tools and work across text, images, documents and video. The model has 120 billion total parameters, with 12 billion active per token, and NVIDIA says developers can customize it with their own data and workflows. The company published the announcement in a [technical blog post](https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/).…