Leverage local models with LMStudio's server.
Extend LMStudio's functionality by running prompts directly to your cursor without having to switch to the LMStudio window. Run any local model on LMStudio's server, write a prompt, highlight your prompt and press control+shift+9 to have your keyboard emulated and the prompt sent to LMStudio's server. The result will be streamed back to your cursor. If you would like to provide context to your prompt copy the context, write a prompt, highlight prompt, and press control+shift+8 to have your keyboard emulated and the context and prompt sent to LMStudio's server. The result will be streamed back to your cursor.
To use the vision capabilities of LMStudio, you will need to find an applicable model with vision capabilities running on local server. Copy the image as path to your clipboard, write prompt, highlight prompt, and press control+shift+7 to have your keyboard emulated and the prompt and image path sent to LMStudio's server. The result will be streamed back to your cursor.
- Google's Gemma 2B Instruct
- Write your prompt
- Highlight your prompt
- Press Control+Shift+9
- The result will be streamed back to your cursor
- Copy your context
- Write your prompt
- Highlight your prompt
- Press Control+Shift+8
- The result will be streamed back to your cursor
- Copy the image as path to your clipboard
- Write prompt
- Highlight prompt
- Press Control+Shift+7
- The result will be streamed back to your cursor
- Cargo run