guard
Nemotron 3.5 Content Safety
NVIDIA's 4B multimodal content safety model with the Aegis 2.0 taxonomy plus a custom-policy mode (safety and prompt injection); licence OpenMDW 1.1 plus Gemma Terms of Use. HF 24 Jun 2026.
Levelmodel
Classguard
Parameters4B
Contextnot in the notes
Released4 Jun 2026
Opennessopen weights restricted
Runs onnot in the notes
Statusactive
Benchmark Results
vendor-reported
Aegis 2.0safety
promptvendor-reported
0.86
04590
Score in F1. Higher is better.
MultiJailsafety
vendor-reported
0.95
04590
Score in F1. Higher is better.
PolyGuardsafety
vendor-reported
0.8
04590
Score in F1. Higher is better.
WildGuardTestsafety
vendor-reported
0.85
04590
Score in F1. Higher is better.
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
finetune
Gemma-3-4B-it is the parent (finetune)high confidencemodel cardWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes
- Total parameters
- 4B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text, image
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights restricted
- Licence
- OpenMDW License v1.1 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- 12 languages; no Indonesian
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperNVIDIAbig tech, USA
NVIDIAbig tech, USAModelNemotron 3.5 Content SafetyNVIDIA, guard
Nemotron 3.5 Content SafetyNVIDIA, guardR&D TopicsGuardrails and Safety Classifiers
Use Casesnone recorded
Who Runs Itnone recorded
Models 1
Organisations 1
Sources
- nvidia/Nemotron-3.5-Content-Safety , Hugging Face huggingface.co https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Nemotron 3.5 Content Safety", https://aurion.semai.id/models/nvidia-nemotron-3-5-content-safety/, records of October 2026.