Skip to content

Nvidia Nemotron Nano 12B V2 VL

Nvidia Nemotron Nano 12B V2 VL is NVIDIA's open 12B multimodal reasoning model with a hybrid Mamba-Transformer architecture, OCRBenchV2 results, and specialized support for document intelligence, video understanding, and RAG pipelines.

ReasoningTool UseVision (Image)
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'nvidia/nemotron-nano-12b-v2-vl',
prompt: 'Why is the sky blue?'
})