Nemotron multimodal model for visual reasoning and agentic AI workflows

Details

FieldValue
idnemotron-nano-12b-v2-vl
familynemotron
modalitytext+image+video->text
context_length128000
max_output_tokens16384
knowledge_cutoff2024-10
release_date2025-10-28
is_open_weightsyes
supports_tool_callyes
supports_reasoningyes
supports_structured_outputno
supports_attachmentyes
input_modalitiestext, image, video
output_modalitiestext

Providers