Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Setup guide - Documented by Continue

Use LM Studio in Continue

Continue has a top-level lmstudio provider in config.yaml. Its default apiBase is http://localhost:1234/v1.

Last verified 3 steps2 official sources

Steps

  1. Step 1.

    Get started with LM Studio (download from lmstudio.ai/download), then add an lmstudio model to your Continue config.yaml.

    YAML
    name: My Config
version: 0.0.1
schema: v1

models:
  - name: <MODEL_NAME>
    provider: lmstudio
    model: <MODEL_ID>
    apiBase: http://<MY_ENDPOINT>/v1 # if running a remote instance of LM Studio
  2. Step 2.

    The default apiBase is http://localhost:1234/v1, so omit apiBase for a local LM Studio server.

  3. Step 3.

    Optional: list the model identifiers LM Studio is serving, to use as <MODEL_ID> (LM Studio docs).

    Terminal
    curl http://localhost:1234/v1/models

Caveats

  • Continue's page uses placeholders (<MODEL_ID>) and links to a qwen-qwen3-coder-30b config on continue.dev for a more advanced example. That config was not fetched.
  • Step 3 comes from LM Studio's docs.
  • The old URL docs.continue.dev/customize/model-providers/more/lmstudio returns 404. The current page is /top-level/lmstudio.

More setup guides

Related reading

FAQ

How do I use LM Studio in Continue?

Continue has a top-level lmstudio provider in config.yaml. Its default apiBase is http://localhost:1234/v1.

What base URL does Continue use for LM Studio?

Point Continue at http://localhost:1234/v1.

Is this an official LM Studio and Continue setup?

Continue documents this setup in its own docs. It was last checked against 2 official pages on October 17, 2026.

Sources

Last verified against 2 official pages.

Newsletter

New models, set up the day they ship

One email per week. New model releases, the coding tools that support them and how to wire them up.