Gemma3

Deploy Google Gemma3 bundled with Open WebUI. Gemma3 is an open source large language model from Google DeepMind. Open WebUI provides a web-based chat interface for interacting with the model.

During deployment, you can choose between two model sizes: 4B for efficient performance or 12B for enhanced capabilities.

1. Deploy Gemma3

 Estimated deployment time: 5–10 minutes

Follow the deployment instructions from the Get started section to configure the app, deploy it, and verify software installation.

For information on the app-specific configurations, see the Configuration options section.

Base distribution and plan

  • Supported distribution: Ubuntu 24.04 LTS
  • Recommended plans: All GPU plan types and sizes can be used. The 4B model requires at least 16GB of RAM, while the 12B model requires at least 32GB of RAM.

Configuration options

Configure the required options to deploy your instance. For additional customization, add advanced options.

The table maps the Cloud Manager UI fields to their corresponding API/CLI keys (stackscript_data) required for automated deployments.

StackScript ID: 1997012

UI fieldAPI/CLI keyDescription
Required options
Limited sudo useruser_nameYour preferred username for the limited sudo user, entered without any capital letters, spaces, or special characters.
When adding a limited sudo user, the user is created with a strong generated password for your new Linode instance, and the account is assigned to the sudo group, which provides elevated permissions when running commands with the sudo prefix.
Note: For easier and more secure access with the sudo user, add an account SSH key for the Cloud Manager user during deployment and select that user as an authorized_user. Their SSH pubkey will be assigned to both the root and limited sudo users.
Open WebUI admin nameopenwebui_login_nameThe name associated with your Open WebUI administrator account, required during initial setup.
Open WebUI admin emailopenwebui_login_emailYour email used to log in to Open WebUI.
Hugging Face API tokenhf_tokenYour Hugging Face API token required to download the Gemma 3 model.
To get the token, create a free Hugging Face account, accept the Gemma license, and then generate the token. Read-only access is sufficient.
Advanced options
Disable root access over SSHdisable_rootApplies to a limited sudo user. To block the root user from logging in over SSH, select Yes. Defaults to No.
Note: When you disable the root user from logging in over SSH and don't provide a valid Account SSH Key assigned to the authorized_user, you can still switch to the root user. To do that, log in as root via the Lish console and run cat /home/$USERNAME/.credentials to view the generated password for the limited sudo user.
Linode API tokentoken_passwordApplies to a custom domain. The Linode API token if you want to use Linode's DNS Manager to manage DNS records for your custom domain. Follow Manage personal access tokens to get your token on your account with Read/Write access to Domains.
  • If you provide the token along with the subdomain and domain, the installation attempts to create DNS records via the Linode API.
  • If you don't provide the token, you need to manually configure your DNS records through your DNS provider and point them to the IP address of the new instance.
SubdomainsubdomainApplies to a custom domain. The subdomain you want to use, like blog for blog.example.com. Use it only if you specify a Domain.
DomaindomainApplies to a custom domain. The domain name you want to use, like example.com. Use it only if you specify a Linode API token.
Email address for new DNS zonesoa_email_addressThe email address for your DNS zone.
Optional data exporter Add-onsadd_onsAn option to include add-ons for your deployment. Possible values are:
  • none (default)
  • alloy
  • node_exporter
  • mysqld_exporter
  • newrelic
Gemma 3 Model Sizegemma3_model_sizeThe size of the Gemma3 model to use. Possible values are:
  • 4B (default)
  • 12B

Notes:

  • After the app deployment completes, the passwords for your Open WebUI admin user and limited sudo user are generated and stored in the .credentials file in the home directory. Log in to your instance as root through the Lish console or SSH, then run cat /home/$USERNAME/.credentials to view its contents.
  • You can automatically configure a custom domain (optional) during deployment. To do that:
    1. First, configure your domain to use Linode’s name servers via your registrar. See Configure your domain's authoritative name servers for details.
    2. Once you complete that, specify the Linode API token, subdomain, and domain for the app in Cloud Manager or via API/CLI/Terraform.

Use API, CLI, or Terraform

In addition to deploying the app to a new Linode instance via Cloud Manager, you can also use the Linode API, CLI, or Terraform. When running the operation, you need to provide the StackScript ID, supported Linux distribution, and app-specific fields along with the standard Linode deployment configurations.

Note: Generate a personal access token to authenticate your API, CLI, or Terraform requests.

curl --location 'https://api.linode.com/v4/linode/instances' \
    --header 'Content-Type: application/json' \
    --header 'Accept: application/json' \
    --header 'Authorization: Bearer abc123def456hij789klm' \
    --data-raw '{
        "region": "us-east",
        "type": "g6-standard-2",
        "image": "linode/ubuntu24.04",
        "label": "my-gemma3-one-click-app",
        "root_pass": "@C0mpl3x#P@ssw0rd",
        "stackscript_id": 1997012,
        "stackscript_data": {
            "user_name":"jsmith",
            "openwebui_login_name":"jsmith-admin",
            "openwebui_login_email":"jsmith-admin@example.com",
            "hf_token": "1a23bc45DE678fg9hIj0klmNop1QrsT2Uv34Wxy5Z67"
        }
    }'
linode-cli linodes create \
    --region us-east \
    --type g6-standard-2 \
    --label my-gemma3-one-click-app \
    --image linode/ubuntu24.04 \
    --root_pass @C0mpl3x#P@ssw0rd \
    --stackscript_id 1997012 \
    --stackscript_data '{"user_name":"jsmith", "openwebui_login_name":"jsmith-admin", "openwebui_login_email":"jsmith-admin@example.com", "hf_token": "1a23bc45DE678fg9hIj0klmNop1QrsT2Uv34Wxy5Z67"}'
resource "linode_instance" "my-linode" {
    region         = "us-east"
    type           = "g6-standard-2"
    label          = "my-gemma3-one-click-app"
    image          = "linode/ubuntu24.04"
    root_pass      = "@C0mpl3x#P@ssw0rd"
    stackscript_id = 1997012
    stackscript_data = {
        "user_name"             = "jsmith"
        "openwebui_login_name"  = "jsmith-admin"
        "openwebui_login_email" = "jsmith-admin@example.com"
        "hf_token"              = "1a23bc45DE678fg9hIj0klmNop1QrsT2Uv34Wxy5Z67"
    }
}

2. Access Open WebUI

Once your app has finished deploying, you can log in to the Open WebUI interface using your browser.

  1. Open your web browser and navigate to one of these:

    • https://DOMAIN/, where DOMAIN can be replaced with your custom domain entered during deployment.
    • Your Linode instance's rDNS domain. For example, https://192-0-2-1.ip.linodeusercontent.com. See the Manage IP addresses on a Linode guide for details on viewing IP addresses and rDNS.
  2. Log in with the admin email and password from the .credentials file.

    To get the credentials, run the sudo cat /home/$USERNAME/.credentials command through the Lish console or SSH. The .credentials file contains:

    • Sudo Username and Password: Your limited sudo user credentials.
    • Open WebUI Admin Name: The admin username for the web interface.
    • Open WebUI Admin Email: The admin email address.
    • Open WebUI Admin Password: The admin password for logging in.
  3. After successfully logging in, you can start chatting with the Gemma3 model.

Work with RAG operations

Open WebUI provides built-in support for RAG (Retrieval Augmented Generation) operations, allowing you to upload documents and chat with them. By default, the deployment supports file uploads up to 100MB.

If you need to upload larger documents, you can modify the NGINX configuration. To do that:

  1. Edit the NGINX virtual host configuration file located at /etc/nginx/sites-enabled/your-domain.
  2. Update the client_max_body_size directive to a larger value. For example, client_max_body_size 500M; for 500MB.
  3. Reload NGINX using sudo systemctl reload nginx.

Additional resources

For more information about the installed packages, see their official documentation.

📘

Note that we can't vouch for the accuracy or timeliness of externally hosted resources.


Did this page help you?