Skip to main content

​
Setup Guide

1

Open LM Studio

Open LM Studio, navigate to the Developer page and select the desired model to load.
Open LM Studio
2

Load the Model

In this example, we’re loading the openai/gpt-oss-20b model.
Load the model
3

Configure in Oryx

  • Navigate to chrome://settings/Oryx or go to Settings → Oryx AI
  • Click Add Provider
  • Select OpenAI Compatible in the Provider Type dropdown
Configure in Oryx
4

Configure the Model

  • Replace the Base URL with LM Studio URL (default: http://localhost:1234/v1/)
  • Set the Model ID to the one you loaded in LM Studio
  • Important: Set the Context Window Size to match your LM Studio configuration
Configure Base URL
5

Use the Model

Select the model in Oryx agent and start using it! 🎉
Ensure the Context Window Size in Oryx matches what you configured in LM Studio to avoid issues with long conversations.

​
Configuration Details

  • Base URL: http://localhost:1234/v1/ - Provider Type: OpenAI Compatible - Context Window: Depends on your model and hardware (typically 2048-32768)
LM Studio supports various models including: - OpenAI GPT-OSS series - LLaMA and derivatives - Mistral models - And many more from Hugging Face