Looking for a powerful server to run your local AI models? Ollama is a perfect choice, designed to operate in a headless setup. Integrated with the AI module, Ollama enables efficient management and execution of AI models on your own infrastructure, giving you full control without the need for a graphical interface.
Features
Ollama acts as a robust server solution for running local models, perfect for developers who need headless operations. Integrated with the AI module, it allows you to run and scale AI models without a GUI, making it ideal for production environments where efficiency and control are key.
Post-Installation
- Set up your API key using the Key module with the details of your local Ollama server.
- Visit /admin/config/ai/providers/ollama and setup your server ip.
- Once configured, you can start running models on your headless Ollama server seamlessly.
Additional Requirements
The AI module.
Supporting this Module
Support the AI module on OpenCollective.
Community Documentation
Supporting organizations:
Initial Development
Project information
- Project categories: Integrations
- Ecosystem: AI (Artificial Intelligence)
328 sites report using this module- Created by marcus_johansson on , updated
Stable releases for this project are covered by the security advisory policy.
There are currently no supported stable releases.
Releases
1.2.0-rc3
released 8 April 2026
Works with Drupal: ^10.2 || ^11
Install:
Development version: 1.2.x-dev updated 6 Apr 2026 at 19:21 UTC
1.1.0-beta2
released 12 June 2025
Works with Drupal: ^10.2 || ^11
Install:
Development version: 1.1.x-dev updated 4 Sep 2025 at 07:34 UTC
1.0.0-beta1
released 29 October 2024
Works with Drupal: ^10.2 || ^11
Install:
Development version: 1.0.x-dev updated 27 Jan 2025 at 07:10 UTC
