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

Setup guide - Documented by Zed

Use LM Studio in Zed

Zed has a built-in LM Studio provider for the Zed Agent, Inline Assistant and similar features. You download a model, start the LM Studio API server, and pick an LM Studio model in the dropdown.

Last verified 5 steps2 official sources

Steps

  1. Step 1.

    Download and install LM Studio (lmstudio.ai/download).

  2. Step 2.

    Download at least one model in LM Studio, or use the LM Studio CLI.

    Terminal
    lms get qwen2.5-coder-7b
  3. Step 3.

    Start the LM Studio API server.

    Terminal
    lms server start
  4. Step 4.

    In Zed, select an LM Studio model from the model dropdown.

  5. Step 5.

    If your LM Studio server requires a key, enter the key in the provider UI or set LMSTUDIO_API_KEY.

Caveats

  • This covers Zed's own AI features only. External Agents and Terminal Threads need separate config (Zed docs).
  • The Zed page does not state a base URL. LM Studio's default server address is http://localhost:1234.
  • The LLM providers docs moved: the LM Studio steps are now at zed.dev/docs/ai/use-a-local-model.

FAQ

How do I use LM Studio in Zed?

Zed has a built-in LM Studio provider for the Zed Agent, Inline Assistant and similar features. You download a model, start the LM Studio API server, and pick an LM Studio model in the dropdown.

Which LM Studio model ids work in Zed?

The official docs read for this guide list qwen2.5-coder-7b.

Is this an official LM Studio and Zed setup?

Zed 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.