Ollama with Open WebUI
Run Ollama with Open WebUI on Polyer to deploy open-weight language models behind a self-hosted chat interface. The template creates a private ollama-api service with model storage on a volume, plus a public Open WebUI service. Polyer has no GPU: models run on CPU, so review memory, CPU and storage before pulling one.
What you can use it for
- Experiment with small open-weight models without sending prompts to an external model provider.
- Offer an internal chat interface for light tasks such as drafting or summarizing short texts.
What this template creates
ollama-api
ollama/ollama:latestPrivate service Persistent volume
open-webui
ghcr.io/open-webui/open-webui:mainPublic endpoint Persistent volume
Configuration to review
This template has no additional declared inputs. Review the generated variables, endpoints and resource settings in the deployment form.
How to deploy
- Select Configure deployment and sign in or create an account.
- Choose a new or existing project and select an available region.
- Review services, required inputs, storage and compatibility warnings. Submit the deployment only when the configuration is ready.
- Inspect deployment logs, complete the application's setup and test its endpoints before production use.
Operating this application
- Create the first Open WebUI account right after deployment, since it becomes the administrator, then pull a small model from the admin settings. The ollama-api service has no public endpoint; Open WebUI reaches it over the private network.
- Polyer has no GPU, so models run on CPU within the memory and CPU limits of the ollama-api service. Only small models are practical, a model larger than the available memory may fail to load, and response speed depends on the CPU you allocate.
- Each downloaded model consumes persistent storage on the /root/.ollama volume, so remove unused models, and back up the Open WebUI data at /app/backend/data. The latest and main image tags change on redeploy, so check release notes or pin versions before upgrading.
Hosting costs
CPU, memory, storage and network usage contribute to your bill. The selected region affects resource prices. A multi-service template incurs usage for each service; external APIs and software licenses are separate.
Review prices and estimate resource costsSource and validation
This deployment configuration comes from Coolify's Apache-2.0 licensed open template collection and is adapted through Polyer's compose importer.
Static compatibility analysis is not a live application verification. Test your chosen configuration and recovery workflow before using it for production.
Editorial content reviewed: 2026-10-10
