NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
Details
| Field | Value |
|---|---|
| id | nvidia/nemotron-3.5-content-safety |
| family | nemotron |
| modality | text+image->text |
| context_length | 131072 |
| max_output_tokens | 117964 |
| release_date | 2026-06-04 |
| is_open_weights | yes |
| supports_tool_call | no |
| supports_reasoning | yes |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | text, image |
| output_modalities | text |