Run open models through the Ollama REST and OpenAI-compatible APIs with persistent model storage.
Launch in your Sealos workspace.
Start with the resources defined by the Ollama template. Review CPU, memory, persistent storage, and network allocations for every service in Canvas. Capacity needs depend on your data and workload; monitor usage as they grow.
Template configuration and setupUse the application URL or connection details shown in Canvas. Follow the deployment guide for first-time account setup or client configuration, and keep generated credentials available for that step.
Sealos monthly plans include compute, memory, storage, and traffic. Size your plan for all deployed services. Software licenses and external AI or API services may have separate terms and charges. Confirm the applicable plan and optional charges in Cost Center.
Compare Sealos resource plansFor current cloud charges, refer to Sealos plan pricing. Upstream documentation may reference earlier billing models.
Ollama runs open models behind a native REST API and an OpenAI-compatible API. This Sealos template deploys the official CPU image with persistent model storage and a generated HTTPS endpoint.
Ollama packages model downloads, runtime management, and generation APIs into one service. Teams can pull models from the Ollama library, keep them on a persistent volume, and call the same endpoint from internal tools, agents, notebooks, or OpenAI-compatible clients.
This template runs ollama/ollama:0.32.5 as a single StatefulSet. Sealos creates the Service, Ingress, persistent model volume, and App entry so the API is reachable from the generated HTTPS URL.
/v1 base URL.The template includes the Kubernetes resources needed to run the Ollama API on Sealos.
Configuration:
ollama/ollama:0.32.5 image.11434 through a Sealos-managed HTTPS Ingress./root/.ollama.1Gi openebs-backup persistent volume for the model store./api/version for startup, readiness, and liveness probes.License Information:
Ollama is available under the MIT License.
The App URL points to the Ollama API. A browser request to / returns Ollama is running.
Set the generated HTTPS endpoint:
export OLLAMA_URL="https://<your-app>.usw-1.sealos.app"
Check the deployed version and available models:
curl "$OLLAMA_URL/api/version"
curl "$OLLAMA_URL/api/tags"
Pull the compact model used for template validation:
curl "$OLLAMA_URL/api/pull" \
-H "Content-Type: application/json" \
-d '{"model":"smollm2:135m","stream":false}'
Generate a response:
curl "$OLLAMA_URL/api/generate" \
-H "Content-Type: application/json" \
-d '{
"model": "smollm2:135m",
"prompt": "What is 2 + 2?",
"stream": false
}'
OpenAI-compatible clients can use $OLLAMA_URL/v1 as their base URL.
| Resource | Default |
|---|---|
| CPU limit | 500m |
| Memory limit | 512Mi |
| Model storage | 1Gi |
| Replicas | 1 |
The defaults were validated on Sealos with smollm2:135m, whose stored model is about 271 MB. Larger models need enough memory for their weights and working buffers, plus a larger persistent volume when their files exceed the available model storage.
The StatefulSet stores downloaded models and metadata in the openebs-backup volume mounted at /root/.ollama. Pod replacements keep this data available. Deleting the template instance and its PVC removes the stored models.
The public HTTPS endpoint reaches the Ollama API directly. Treat the generated host as a sensitive service endpoint and place an authenticated gateway, allowlist, or private network boundary in front of shared deployments.
Ollama is runningThat response means the API process is available. Pull a model through /api/pull, then call /api/generate or the OpenAI-compatible /v1 endpoints.
Large model files take longer to download and write to the persistent volume. Start with compact models such as smollm2:135m, then increase storage and memory before pulling larger models.
Increase memory for the StatefulSet. Model weights and runtime buffers must fit inside the selected memory limit.
This template follows the upstream MIT License.
A shorter path from an app you want to an app you can run. Sealos brings deployment and ongoing operations into one place.
Start with a ready-made template. Review its configuration and launch from the Sealos console.
Run on managed infrastructure with built-in workload scheduling and recovery.
Give your application a public HTTPS endpoint with certificates managed for you.
Keep application data on persistent volumes across container restarts.
Adjust CPU, memory, and replicas from the console as your workload changes.
Sealos provisions the resources defined by your template and brings them together in your workspace.
Container workloads with configurable CPU, memory, and replicas.
An address for your app, with managed TLS certificates.
A database provisioned alongside your app when the template calls for one.
Storage for the files and data your application needs to keep.
Application settings and secrets configured in one place.
Inspect container logs and resource usage from the console.
Resources and their configuration vary by template. Review the deployment form for this app’s exact setup.
Explore more production-ready templates.
Build production-ready ai templates with Sealos.
Open Design is a local-first, open-source AI design workspace for generating prototypes, decks, images, videos, and design-system-driven artifacts.
Build production-ready ai templates with Sealos.
Host OpenClaw's AI agent gateway on Sealos with a browser control panel, token authentication, and persistent storage for configuration and workspaces.
Build production-ready ai templates with Sealos.
Open-source AI model gateway compatible with the OpenAI API, with multi-provider routing, quota management, channel orchestration, and an admin dashboard.