LM Studio

Run local models with LM Studio in Kern agents.

Run Large Language Models locally with LM Studio

LM Studio is a fantastic tool for running models locally.

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 are powerful, while being really small in size.

Set up a model

Install LM Studio, download the model you want to use, and run it.

Example

After you have the model locally, use the LM Studio model class to access it

1from kern.agent import Agent
2from kern.models.lmstudio import LMStudio
3
4agent = Agent(
5    model=LMStudio(id="qwen2.5-7b-instruct-1m"),
6    markdown=True
7)
8
9# Print the response in the terminal
10agent.print_response("Share a 2 sentence horror story.")

Note View more examples here.

Params

Parameter	Type	Default	Description
`id`	`str`	`"lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF"`	The id of the LMStudio model to use
`name`	`str`	`"LMStudio"`	The name of the model
`provider`	`str`	`"LMStudio"`	The provider of the model
`api_key`	`Optional[str]`	`None`	The API key for LMStudio (usually not needed for local)
`base_url`	`str`	`"http://localhost:1234/v1"`	The base URL for the local LMStudio server

LM Studio also supports the params of OpenAI.