So far I’ve always used Ollama as a way to run LLM's locally on my development machine. However recently I discovered the Podman AI Lab extension as an alternative solution to work with Large Language Models on your local machine.
In this post I’ll share my experience when trying the Podman AI lab extension.
Remark: I assume you already have Podman Desktop up and running on your machine. (If not check one of my previous posts; Kubernetes–Setup a local cluster through Podman Desktop)
Installation
You need to have at least the following versions to get started:
If the prerequisites are ok, installing the extension should be really easy. Based on the documentation it should be sufficient to click on the installation link to get going. Unfortunately this didn’t work on my machine and I got the following error message instead:
Turns out that the update had failed for an unknown reason and that I was still running an older Podman Desktop version. After updating, I could go to the Extension Catalog and install the Podman AI lab extension:
After installation, an extra icon appears on the left:
Interact with an LLM locally
Now that the extension itself is up and running, we can download a model. Therefore go to the model catalog and click on the download icon next to one of the listed models:
Downloading a model can take some time, so the ideal moment to grab a coffee…
Once the model is downloaded you can start a model service. A model service is an inference server that is running in a container and exposes the model through a REST api.
Go to the Services tab and click on the New Model Service on the top right:
Choose the downloaded model from the list and click on Create Service:
Once the service is started you can generate a code snippet to interact with the model:
Model playground
If you want to interact with the model directly without writing your own code, you can use the built-in playground.
Therefore go to Playgrounds and click on New Playground on the top right:
Choose the downloaded model and click on Create Playground:
Once the playground is ready, you get a chat interface to interact with the model:
Nice!
More information
Running large language models locally using Ollama (bartwullems.blogspot.com)
Podman AI Lab | Podman Desktop (podman-desktop.io)