Moderation and safety

Qwen3Guard

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.

Developer
Alibaba (Qwen), China
First release
Sep 2025
Latest release
Sep 2025
Sizes
0.6B – 8B
License
Commercial use allowedApache 2.0
Russian
Supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Security, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Filtering bot requests in Russian
  • Stopping a dangerous reply during generation
  • Labeling messages by risk category

Where it is used

Chatbots and AI assistantsCommunity moderationCustomer support

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. Qwen3Guard-Stream 0.6B, 4B, 8B
  2. Qwen3Guard-Gen 0.6B, 4B, 8B

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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Qwen3Guard be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Qwen3Guard 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 Qwen3Guard support Russian?

Yes, Russian is listed on the model card.

Where can I download Qwen3Guard and what does it cost?

The Qwen3Guard 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 safetyAegis / Nemotron Safety GuardNVIDIA · USACommercial use with conditions

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.

DetailsModeration and safetyGranite GuardianIBM · USACommercial use allowed

IBM judge models: they catch harm, profanity and jailbreak attempts, and in RAG and agents check whether an answer is grounded in the documents. You can state your own rule in words.

Details

Source: huggingface.co/Qwen/Qwen3Guard-Stream-8B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.