Self-host Hollama with Levelrail
A minimal web chat client for Ollama and OpenAI compatible servers. MIT licensed. Add the address of your model server in settings.
- Authorfmaclen
- LicenceMIT
- Memory64 MiB
- Services1
How to self-host Hollama
-
Pull the images
One image is pulled on your server.
Show images
ghcr.io/fmaclen/hollama:0.37.0
-
Create the app
One service starts in a single Compose app, on port 4173.
-
Fill in the secrets
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.
After the first start
- Open Settings and set the address of your Ollama or OpenAI compatible server.
Hollama requirements
- Memory
- About 64 MiB
- Architectures
- amd64 unknown, arm64 unknown
- Ports
- 4173
- 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.
Install Levelrail first
On a server with Levelrail running, run the command above, or open the dashboard: Apps, New app, Browse templates, then Hollama. 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 Hollama docs page.
Deploy Hollama your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy Hollama from the CLI
levelrail-cli templates deploy hollama --name my-hollama Deploy Hollama with the API
curl -X POST -H "Authorization: Bearer $TOKEN" \
https://levelrail.example.com/api/v1/service-templates/hollama/deploy Hollama configuration
Hollama services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| hollama | ghcr.io/fmaclen/hollama:0.37.0 | 4173 | none |
Hollama environment variables
The catalog lists no environment variables for this template.
Ports and volumes
- Ports
- 4173
- Volumes
- none
Hollama FAQ
How much memory does Hollama need?
The catalog lists about 64 MiB of memory for Hollama.
Does Hollama run on arm64?
For Hollama, arm64 support is not confirmed; amd64 is unknown.
What licence is Hollama under?
Hollama is licensed under MIT, which is permissive, with few conditions on reuse.
Does Hollama need configuration before it starts?
No. The template fills in its own defaults.
Which ports does Hollama use?
Hollama listens on port 4173 inside the stack.
Can I deploy Hollama 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 Hollama, 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 ghcr.io/fmaclen/hollama:0.37.0 is what you deploy there.