← 模型广场
N

Nemotron Nano 12b V2 Vl

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

图像理解工具调用推理流式

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...

参数

上下文

128,000 tokens

输入模态

image, text, video

输出模态

text

发布:2025-10

支持参数

include_reasoningmax_tokensreasoningseedtemperaturetool_choicetoolstop_p

开放权重 · HuggingFace

150,225 月下载
83 收藏
other image-text-to-text
在 HuggingFace 查看 →