How to use LM Studio locally

LM Studio includes a command line tool for working with local models. Its documented commands inspect the application, list models, and load a model.

Use LM Studio version zero point two point twenty two or newer. The command line tool ships with that application.

1. Step 1. Set up the official tool

   Use the installation instructions for your system.

   npx lmstudio install-cli

   The documented tool is available for the usage steps.

2. Step 2. Check application status

   Check the status of the local application. This operation reports its current state before you move on to working with models.

   lms status

   Check the status of the local application.

3. Step 3. List downloaded models

   List the models that have already been downloaded. The list shows which models are available locally before you choose one to load.

   lms ls

   List the models that have already been downloaded.

4. Step 4. Load a model

   Load a model for inference. Use the documented loading operation for the model you want to make available in the local application.

   lms load

   Load a model for inference.

List all loaded models available for inference. Compare the list of loaded models with the model selected during the loading step.

lms ps

Start the local API server. This is the interface described in the guide for using the application through its local server.

Read the documented requirements before running the commands.

Commands were checked against official documentation. This guide does not include a repository security certification.

• Official documentation