Moderation and safety

Granite Guardian

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.

Developer
IBM, USA
First release
Sep 2024
Latest release
Apr 2026
Sizes
38M – 8B
License
Commercial use allowedApache 2.0
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Security, Finance, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Checking bot requests and replies
  • Finding made-up facts in knowledge-base answers
  • Checking your own rules written as text

Where it is used

Chatbots and AI agentsBanking and insuranceQuality control of AI systems

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. Granite Guardian 4.1 8B
  2. Granite Guardian 3.3 8B
  3. Granite Guardian 3.2 5B и 3B-A800M
  4. Granite Guardian 3.1
  5. Granite Guardian 3.0 2B и 8B
  6. Granite Guardian HAP 38M и 125M (токсичность)

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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 Granite Guardian 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 Granite Guardian 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 Granite Guardian support Russian?

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

Where can I download Granite Guardian and what does it cost?

The Granite Guardian 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.

DetailsTextIBM GraniteIBM · USACommercial use allowed

IBM enterprise models with transparent training data and ISO 42001 certification. Granite 4 is a memory-efficient Mamba and Transformer hybrid.

Details

Source: huggingface.co/ibm-granite/granite-guardian-4.1-8b. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.