Moderation and safety

Aegis / Nemotron Safety Guard

NVIDIA content filters for bots, with separate models for keeping the conversation on topic and detecting jailbreaks. Safety Guard v3 was trained on 9 languages; Russian was tested only without fine-tuning.

Developer
NVIDIA, USA
First release
Apr 2024
Latest release
May 2026
Sizes
4B – 8B
License
Commercial use with conditionsNVIDIA and OpenMDW licenses together with the base model terms (Llama, Gemma)
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Security, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Checking bot requests and replies
  • Keeping the bot within its topic
  • Detecting attempts to bypass rules

Where it is used

Chatbots and AI assistantsCustomer supportContent moderation

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Nemotron-3.5 Content Safety
  2. Nemotron-3 Content Safety
  3. Nemotron Content Safety Reasoning 4B
  4. Llama-3.1-Nemotron-Safety-Guard-8B-v3
  5. NemoGuard 8B: безопасность и контроль темы
  6. Aegis Content Safety 1.0

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Aegis / Nemotron Safety Guard be used in a commercial project?

With conditions. License: NVIDIA and OpenMDW licenses together with the base model terms (Llama, Gemma). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Aegis / Nemotron Safety Guard need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Aegis / Nemotron Safety Guard support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Aegis / Nemotron Safety Guard and what does it cost?

The Aegis / Nemotron Safety Guard weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Moderation and safetyLlama GuardMeta · USACommercial use with conditions

Filter models that check chatbot requests and replies for dangerous topics against a list of categories. Version 4 also checks images. Russian is not officially supported.

DetailsModeration and safetyQwen3GuardAlibaba (Qwen) · ChinaCommercial use allowed

Safety filters for 119 languages, Russian among them. The Stream version checks a bot's reply while it is being generated and can cut it off on the fly.

DetailsTextNVIDIA NemotronNVIDIA · USACommercial use with conditions

NVIDIA models for agents and reasoning, optimized to run fast on its GPUs. Nemotron 3 is a Mamba and MoE hybrid from 4B to 550B; Nano Omni handles video, audio and images (English only).

Details

Source: huggingface.co/nvidia/Nemotron-3.5-Content-Safety. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.