Nemotron multimodal model for visual reasoning and agentic AI workflows
Details
| Field | Value |
|---|---|
| id | nemotron-nano-12b-v2-vl |
| family | nemotron |
| modality | text+image+video->text |
| context_length | 128000 |
| max_output_tokens | 16384 |
| knowledge_cutoff | 2024-10 |
| release_date | 2025-10-28 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | text, image, video |
| output_modalities | text |