Ollama
Image: ollama/ollama:latest
- Port 11434/tcp
- 30 GB volume at /root/.ollama
- 4 vCPU · 8 GB
Template · AI & LLM
ChatGPT-style UI for local models, wired to an Ollama service.
Opens the dashboard with this template pre-selected. Sign in with GitHub if you are new; the free tier needs no card.
2 services in the environment you pick, on the private network of the project.
ghcr.io/open-webui/open-webui:main talking to ollama/ollama on the private network. First sign-up becomes admin.
Image: ollama/ollama:latest
Image: ghcr.io/open-webui/open-webui:main
Generated secrets never leave the platform; references are resolved on the private network. Anything marked required is asked for at deploy time.
| Name | Value |
|---|---|
| OLLAMA_HOST | 0.0.0.0:11434 |
| OLLAMA_BASE_URL | http://${{self.SKIFFLY_PRIVATE_DOMAIN}}:11434 |
| Name | Value |
|---|---|
| OLLAMA_BASE_URL | ${{Ollama.OLLAMA_BASE_URL}} |
| WEBUI_SECRET_KEY | generated (secret) |
| WEBUI_URL | https://${{self.SKIFFLY_PUBLIC_DOMAIN}} |
Volumes, secrets and domain pre-wired. Runs on EU nodes, paid per minute from a prepaid balance.