NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...
Specifications
- Provider
- NVIDIA
- Type
- Open-source / open-weight
- Modality
- text+image+video->text
- Context window
- 128K
- Released
- October 28, 2025
Capabilities
Input: imageInput: textInput: videoOutput: text
Strengths
include_reasoningmax_tokensreasoningseedtemperaturetool_choicetoolstop_p
