Moderation and safety

ShieldGemma

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

Developer
Google, USA
First release
Jul 2024
Latest release
Mar 2025
Sizes
2B – 27B
License
Commercial use with conditionsGemma Terms of Use: commercial use allowed with restrictions on types of use
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Security, Customer support
Deploy on your server Hugging Face

What it does

  • Moderating user messages
  • Checking bot replies
  • Checking generated images before publishing

Where it is used

Content moderationChatbotsImage generation services

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. ShieldGemma 2 4B (картинки)
  2. ShieldGemma 2B, 9B, 27B

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 ShieldGemma be used in a commercial project?

With conditions. License: Gemma Terms of Use: commercial use allowed with restrictions on types of use. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does ShieldGemma 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 ShieldGemma support Russian?

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

Where can I download ShieldGemma and what does it cost?

The ShieldGemma 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.

Comparisons

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.

DetailsModeration and safetyWildGuardAi2 (Allen Institute for AI) · USACommercial use allowed

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.

Details

Source: huggingface.co/google/shieldgemma-2-4b-it. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.