Setup guide - Documented by Roo Code
Use LM Studio in Roo Code
Roo Code has a built-in LM Studio API provider that connects to LM Studio's OpenAI-compatible local server at http://localhost:1234 by default.
Last verified 5 steps1 official source
Steps
- Step 1.
Download and install LM Studio. Use the LM Studio interface to search for and download a model in GGUF format.
- Step 2.
Start the local server: open LM Studio, click the "Local Server" tab (the icon looks like <->), select the model you downloaded, and click "Start Server".
- Step 3.
Open Roo Code settings (gear icon) and choose "LM Studio" from the "API Provider" dropdown.
- Step 4.
Enter the Model ID: the file name of the model you loaded in LM Studio (e.g., codellama-7b.Q4_0.gguf). You can find this in the LM Studio "Local Server" tab.
- Step 5.
(Optional) Base URL: by default Roo Code connects to LM Studio at
http://localhost:1234. If LM Studio uses a different address or port, enter the full URL here.
Caveats
- Roo's example model id (codellama-7b.Q4_0.gguf) and the 'Local Server tab' UI wording are dated. Newer LM Studio docs start the server from the Developer tab or with lms server start, and serve ids like openai/gpt-oss-20b.
- Roo docs troubleshooting: if you see "Please check the LM Studio developer logs to debug what went wrong" you may need to adjust the context length settings in LM Studio.
- docs.roocode.com now redirects to roocodeinc.github.io/Roo-Code.
More setup guides
Same tool, other providers
Related reading
- LM Studio Bionic: A Local-First AI Agent for Open ModelsLM Studio launches Bionic, a standalone agent harness for open models with local inference, voice input, and zero data retention cloud options.
- Ollama vs LM Studio vs vLLM vs llama.cpp: Picking a Local Runtime for Coding AgentsOllama vs LM Studio vs vLLM vs llama.cpp for coding agents: what each local runtime is for, where they overlap, and which to pick for your setup.
FAQ
How do I use LM Studio in Roo Code?
Roo Code has a built-in LM Studio API provider that connects to LM Studio's OpenAI-compatible local server at http://localhost:1234 by default.
Which LM Studio model ids work in Roo Code?
The official docs read for this guide list codellama-7b.Q4_0.gguf. Requests go to http://localhost:1234.
Is this an official LM Studio and Roo Code setup?
Roo Code documents this setup in its own docs. It was last checked against 1 official page on October 17, 2026.
Sources
Last verified against 1 official page.
- roocodeinc.github.iohttps://roocodeinc.github.io/Roo-Code/providers/lmstudio/
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.