Nemotron 3.5 Super VL
NVIDIA · US · #8 in our ranking · Best for documents and screens
Nemotron 3.5 Super VL is an open-weight mixture-of-experts model from NVIDIA (United States), released Oct 2026, with 120B parameters (12B active per token), a 1M-token context window, and the OpenMDW-1.1.
A hybrid Mamba-Transformer mixture-of-experts with a vision encoder. It reads page images, screenshots, and video alongside text, and NVIDIA says it serves on 4 H100s or 2 GB200s.
Nemotron 3.5 Super VL specs
- Provider
- NVIDIA
- Origin
- US
- Architecture
- Mixture-of-experts
- Parameters
- 120B total · 12B active
- Context
- 1M tokens | 786K words
- License
- OpenMDW-1.1 Commercial use
- Input
- Text, Image, Video
- Released
- Oct 2026
- Weights
- Hugging Face
Sourced from the model card on Hugging Face. Last checked 2026-10-16.
Highlights
- 120B total, 12B active
- Text, image, and video input
- Permissive OpenMDW license
Where it fits for payment teams
Good for agents that read scanned documents and portal screenshots, like KYB packets or dispute evidence.
Harnesses in Runtime
Run Nemotron 3.5 Super VL through any of these harnesses on Runtime.
Provider-reported benchmarks
| SWE-bench Verified | 71.1 |
|---|---|
| Terminal-Bench 2.1 | 60.7 |
| BrowseComp | 78 |
Benchmark scores are reported by each model provider on its Hugging Face model card. They are not independently verified by Runtime.
How to run Nemotron 3.5 Super VL
Download the weights
Pull nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 from Hugging Face. Check the OpenMDW-1.1.
Serve it in your cloud
vLLM or SGLang on your GPUs, or a managed host.
Put it to work in Runtime
Point an agent or skill at it, then compare with evals.
Nemotron 3.5 Super VL FAQ
What is the context window of Nemotron 3.5 Super VL?
+
Nemotron 3.5 Super VL supports a 1M-token context window (1,048,576 tokens), roughly 786K words of English text.
How many parameters does Nemotron 3.5 Super VL have?
+
Nemotron 3.5 Super VL is a mixture-of-experts model with 120B total parameters, of which 12B are active per token.
Is Nemotron 3.5 Super VL free for commercial use?
+
Yes. Nemotron 3.5 Super VL is released under the OpenMDW-1.1 license, which is permissive and allows commercial use and fine-tuning.
What can Nemotron 3.5 Super VL take as input?
+
Nemotron 3.5 Super VL accepts text, image, video input and generates text.
Can I run Nemotron 3.5 Super VL in my own cloud with Runtime?
+
Yes. Download the weights from Hugging Face (nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16) and serve them with vLLM or SGLang in your cloud, or use a managed provider that hosts the model. Runtime agents can then use Nemotron 3.5 Super VL through a harness like OpenCode, with your data staying in your environment.