NVIDIA introduces Nemotron 3.5 Super VL for multimodal agents
NVIDIA announced an open model combining text, image, document and video understanding with reasoning and tool use.
Event / data period: 2026-10-15
Published: · Updated:
NVIDIA announced Nemotron 3.5 Super VL on October 15 as an open, customizable multimodal model. Its technical post describes a 120-billion-parameter mixture-of-experts architecture that activates 12 billion parameters per token and combines visual and text understanding with reasoning and tool use.
The company reported up to five times the throughput of other open models in its size category on agent tasks with a single GPU. NVIDIA also shared results from customers adapting the model to specialized workflows. These are company-reported comparisons and customer results, not independent measurements in a common test.
Data
NVIDIA introduces Nemotron 3.5 Super VL for multimodal agents
NVIDIA announced an open model combining text, image, document and video understanding with reasoning and tool use.
- · Occurred
NVIDIA introduces Nemotron 3.5 Super VL for multimodal agents
NVIDIA announced an open model combining text, image, document and video understanding with reasoning and tool use.
Methodology
This structured record summarizes the cited announcement; it is not an independent performance evaluation.
Updated:
Subjects and places
Subject proposals
- Science and technologySuggested
- Preserved editorial category/topic; broad candidate onlydeveloper.nvidia.com ↗
Geographic references
Only source-provided geographic references are shown. Opening an external map is optional. Optional story maps use OpenStreetMap. Opening a map sends your IP address and this site’s address to the map provider; location data remains readable as text without loading the map.
- United States · Place role: Coverage · Place type: Country or area · Location precision: RegionalEvidence
- Explicit preserved editorial country/region; no city or national centroid inferreddeveloper.nvidia.com ↗