LLM EXPLORER 57,918 MODELS INDEXED

Nemotron 3 Content Safety by nvidia

By nvidia · 1706 downloads
HF Repo ↗ Copy URL

Nemotron 3 Content Safety is an open-source language model by nvidia. Features: 4b LLM, VRAM: 8.6GB, License: other, LLM Explorer Score: 0.26.

  Ar Base model:finetune:google/gem... Base model:google/gemma-3-4b-i...   Conversational   De   En   Endpoints compatible   Es   Fr   Gemma3   Hi   Image-text-to-text   It   Ja   Ko   Nl   Region:us   Safetensors   Sharded   Tensorflow   Th   Zh
Model Card on HF 🤗: https://huggingface.co/nvidia/Nemotron-3-Content-Safety 

Nemotron 3 Content Safety Parameters and Internals

LLM NameNemotron 3 Content Safety
Repository 🤗https://huggingface.co/nvidia/Nemotron-3-Content-Safety 
Base Model(s)  Gemma 3 4B It   google/gemma-3-4b-it
Model Size4b
Required VRAM8.6 GB
Updated2026-08-10
Maintainernvidia
Model Typegemma3
Model Files  0.8 GB: 1-of-5   2.0 GB: 2-of-5   2.0 GB: 3-of-5   2.0 GB: 4-of-5   1.8 GB: 5-of-5
Supported Languagesen ar de es fr hi ja th nl it ko zh
Model ArchitectureGemma3ForConditionalGeneration
Licenseother
Transformers Version4.57.6
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Nemotron 3 Content Safety

Best Alternatives
Context / RAM
Downloads
Likes
Medgemma 4B It Abliterated128K / 6.3 GB136
Gemma 3 Glitter 4B128K / 8.6 GB3347
Fallen Gemma3 4B V1128K / 8.6 GB1318
Gemma 3 4B It0K / 8.6 GB18552621345
Translategemma 4B It0K / 8.6 GB38998793
...on Content Safety Reasoning 4B0K / 10 GB869029
Medgemma 1.5 4B It0K / 8.6 GB29369
Gemma 3 4B Pt0K / 8.6 GB72499159
...Gemma 3 4B It Datav3 Only Mask0K / 8.6 GB910
Medgemma 1.5 4B It Bf160K / 9.9 GB58511
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Nemotron-3-Content-Safety.