Moderation and safety

WildGuard

An open Ai2 filter: in a single pass it determines whether a request is harmful, whether a reply is harmful, and whether the bot refused needlessly. Works in English.

The last open version came out in Jun 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Ai2 (Allen Institute for AI), USA
First release
Jun 2024
Latest release
Jun 2024
Sizes
7B
License
Commercial use allowedApache 2.0
Russian
Not supported
Ready-made builds
GGUF
Running
On your own serverNeeds a GPU
Industries
Security
Deploy on your server Hugging Face GitHub

What it does

  • Checking requests to the bot
  • Checking bot replies
  • Finding unnecessary bot refusals on harmless questions

Where it is used

ChatbotsQuality control of AI systems

Hardware requirements

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

Versions

  1. WildGuard 7B

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 WildGuard 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 WildGuard need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does WildGuard support Russian?

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

Where can I download WildGuard and what does it cost?

The WildGuard 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 safetyShieldGemmaGoogle · USACommercial use with conditions

Gemma-based filters: they check text for dangerous and offensive content, and ShieldGemma 2 checks images. Focused on English.

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/allenai/wildguard. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.