Self-host LocalAI with Levelrail
A drop-in OpenAI-compatible API that runs language, image, and speech models on your own hardware.
- Authormudler
- LicenceMIT
- Memory4 GiB
- Archarm64
- Services1
How to self-host LocalAI
-
Pull the images
One image is pulled on your server.
Show images
localai/localai:v3.7.0
-
Create the app
One service starts in a single Compose app, with 1 named volume mount for your data, on port 8080.
-
Fill in the secrets
1 setting is preset, you do not have to fill in anything.
-
Open it
Without a domain the app gets an sslip.io address; add --domain SERVICE=HOST to use your own.
LocalAI requirements
- Memory
- About 4 GiB
- Architectures
- amd64 image published, arm64 image published
- Ports
- 8080
- 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 8080 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 LocalAI. 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 LocalAI docs page.
Deploy LocalAI your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy LocalAI from the CLI
levelrail-cli templates deploy localai --name my-localai Deploy LocalAI with the API
curl -X POST -H "Authorization: Bearer $TOKEN" \
https://levelrail.example.com/api/v1/service-templates/localai/deploy LocalAI configuration
LocalAI services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| localai | localai/localai:v3.7.0 | 8080 | localai_models -> /models |
LocalAI environment variables
| Variable | Service | Value |
|---|---|---|
| MODELS_PATH | localai | Preset by the template |
Ports and volumes
- Ports
- 8080
- Volumes
- 1 named mount: localai_models -> /models
LocalAI FAQ
How much memory does LocalAI need?
The catalog lists about 4 GiB of memory for LocalAI.
Does LocalAI run on arm64?
For LocalAI, an arm64 image is published; amd64 is image published.
What licence is LocalAI under?
LocalAI is licensed under MIT, which is permissive, with few conditions on reuse.
Does LocalAI need configuration before it starts?
No. The template fills in its own defaults.
Which ports does LocalAI use?
LocalAI listens on port 8080 inside the stack.
Where does LocalAI keep its data?
In a named volume: localai_models mounted at /models.
Can I deploy LocalAI 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 LocalAI, 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 localai/localai:v3.7.0 is what you deploy there.