Self-host Ollama: Phi-3 Mini with Levelrail

Microsoft's Phi-3 Mini (3.8B), the smallest model in this catalog, good for constrained nodes.

  • Authorollama
  • LicenceMIT
  • Memory4 GiB
  • Archarm64
  • Services1

How to self-host Ollama: Phi-3 Mini

  1. Pull the images

    One image is pulled on your server.

    Show images
    • ollama/ollama:0.33.3
  2. Create the app

    One service starts in a single Compose app, with 1 named volume mount for your data, on port 11434.

  3. Fill in the secrets

    You do not have to fill in anything.

  4. Open it

    Without a domain the app gets an sslip.io address; add --domain SERVICE=HOST to use your own.

Ollama: Phi-3 Mini requirements

Memory
About 4 GiB
Architectures
amd64 image published, arm64 image published
Ports
11434
Domain
Optional, an sslip.io address is used without one
Settings
none to fill in
License
MIT, permissive license
  • Listed. It is in the catalog but not verified. Back up the data volume before changing an image tag.
  • Host ports. It publishes port 11434 on the host, so open them in the VPS firewall only if you want that.

Install Levelrail first

On a server with Levelrail running, run the command above, or open the dashboard: Apps, New app, Browse templates, then Ollama: Phi-3 Mini. New to Levelrail? Install it on a fresh VPS first.

docker pull ghcr.io/glincker/levelrail:latest

Then levelrail-cli login --device. See Getting started and the Ollama: Phi-3 Mini docs page.

Deploy Ollama: Phi-3 Mini your way

Every format below deploys the same pinned images. Pick the one that fits how you work.

Deploy Ollama: Phi-3 Mini from the CLI

levelrail-cli templates deploy ollama-phi --name my-ollama-phi

Deploy Ollama: Phi-3 Mini with the API

Create a token in the dashboard first. This one-click route deploys it as a trial app you can keep or remove.

curl -X POST -H "Authorization: Bearer $TOKEN" \
  https://levelrail.example.com/api/v1/service-templates/ollama-phi/deploy

Ollama: Phi-3 Mini configuration

Ollama: Phi-3 Mini services

ServiceImagePortsVolumes
ollama ollama/ollama:0.33.3 11434 ollama_data -> /root/.ollama

Ollama: Phi-3 Mini environment variables

The catalog lists no environment variables for this template.

Ports and volumes

Ports
11434
Volumes
1 named mount: ollama_data -> /root/.ollama

Ollama: Phi-3 Mini FAQ

How much memory does Ollama: Phi-3 Mini need?

The catalog lists about 4 GiB of memory for Ollama: Phi-3 Mini.

Does Ollama: Phi-3 Mini run on arm64?

For Ollama: Phi-3 Mini, an arm64 image is published; amd64 is image published.

What licence is Ollama: Phi-3 Mini under?

Ollama: Phi-3 Mini is licensed under MIT, which is permissive, with few conditions on reuse.

Does Ollama: Phi-3 Mini need configuration before it starts?

No. The template fills in its own defaults.

Which ports does Ollama: Phi-3 Mini use?

Ollama: Phi-3 Mini listens on port 11434 inside the stack.

Where does Ollama: Phi-3 Mini keep its data?

In a named volume: ollama_data mounted at /root/.ollama.

Can I deploy Ollama: Phi-3 Mini on Dokploy or Dokku?

The services and pinned images on this page can be run on any Docker host. The public Dokploy templates list we compared does not have an entry with the same id for Ollama: Phi-3 Mini, so on Dokploy you would use a Docker Compose application with the file from this page. Dokku deploys container images with its own commands, so the pinned image ollama/ollama:0.33.3 is what you deploy there.

levelrail-cli templates deploy ollama-phi --name my-ollama-phi