LM Studio

Run local models with LM Studio in Agno agents.

LM Studio runs open-source models locally through a desktop app with an OpenAI-compatible local server.

LM Studio supports multiple open-source models. See the library here.

We recommend experimenting to find the best-suited model for your use case. Here are some general recommendations:

  • llama3.3 models are good for most basic use cases.
  • qwen models perform specifically well with tool use.
  • deepseek-r1 models have strong reasoning capabilities.
  • phi4 models offer strong performance at a small size.

Set up a model

Install LM Studio, download and load a model, then open Developer and start the API server on port 1234. Keep the server running while you run Python in a terminal.

Check the model list:

curl http://127.0.0.1:1234/v1/models

Set LMStudio(id=...) in the example to the exact model id returned by your server. If you change the server port, set the matching base_url on LMStudio.

Example

After you have the model locally, use the LMStudio model class to access it. It uses the OpenAI client, so install the openai package:

uv pip install -U openai agno
from agno.agent import Agent
from agno.models.lmstudio import LMStudio

agent = Agent(
    model=LMStudio(id="qwen2.5-7b-instruct-1m"),
    markdown=True
)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story.")
View more examples here.

Params

ParameterTypeDefaultDescription
idstr"qwen2.5-7b-instruct-1m"The id of the LMStudio model to use
namestr"LMStudio"The name of the model
providerstr"LMStudio"The provider of the model
api_keyOptional[str]"not-provided"The API key for LMStudio (usually not needed for local)
base_urlstr"http://127.0.0.1:1234/v1"The base URL for the local LMStudio server

LMStudio is a subclass of the OpenAILike class and has access to the same params.