Meet NVIDIA Nemotron 3.5 Super VL Our new open model combines...
NVIDIA AI@NVIDIAAI
10 views
Oct 16, 2026
~1 min read
Advertisement
1
Meet NVIDIA Nemotron 3.5 Super VL
Our new open model combines reasoning and tool use with text, image, document, and video understanding for long-running AI agents.
120B total parameters with 12B active 🧵
Our new open model combines reasoning and tool use with text, image, document, and video understanding for long-running AI agents.
120B total parameters with 12B active 🧵
1:20
2
Agents may need to read documents, interpret charts, and search the web to complete a task.
Nemotron 3.5 Super VL brings text and visual understanding into one model, reducing the need to pass context between separate text and vision models.
Nemotron 3.5 Super VL brings text and visual understanding into one model, reducing the need to pass context between separate text and vision models.
3:01
3
Nemotron 3.5 Super VL completes 10,000 coding tasks up to 4x faster while maintaining strong SWE-Bench Pro accuracy.
4
Teams are already post-training Nemotron 3.5 Super VL for tasks in document intelligence, cybersecurity, finance, scientific experimentation, and travel.
The chart below shows how accuracy improves when the model is post-trained for each task.
The chart below shows how accuracy improves when the model is post-trained for each task.
0:12
5
Nemotron 3.5 Super VL pairs strong reasoning with high output speed, even at 100K input tokens. See how it compares on @ArtificialAnlys 👇
6
How we built Nemotron 3.5 Super VL, including its post-training approach, multi-token prediction, and inference optimizations: nvda.ws/3Wqw7i6
As always, NVIDIA Nemotron 3.5 Super VL is open and customizable. This includes weights, data and recipes. Available now on @huggingface → huggingface.co/nvidia/NVIDIA-…
As always, NVIDIA Nemotron 3.5 Super VL is open and customizable. This includes weights, data and recipes. Available now on @huggingface → huggingface.co/nvidia/NVIDIA-…