← All models
N

NVIDIA: Nemotron Nano 12B 2 VL (free)

nvidia/nemotron-nano-12b-v2-vl:free

VisionTool useReasoningStreaming

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...

Specs

Context

128,000 tokens

Input

image, text, video

Output

text

Released: 2025-10

Supported parameters

include_reasoningmax_tokensreasoningseedtemperaturetool_choicetoolstop_p

Open weights · HuggingFace

150,225 downloads/mo
83 likes
other image-text-to-text
View on HuggingFace →