What are the most useful LM Studio keyboard shortcuts?

The most essential LM Studio shortcuts are: Ctrl + N (New chat), Ctrl + Shift + N (New window), Ctrl + , (Settings). These cover the most frequent actions and can significantly speed up your workflow.

What is the LM Studio shortcut for new chat?

The LM Studio shortcut for new chat is Ctrl + N on Windows or Cmd + N on Mac. Start a new conversation.

What is the LM Studio shortcut for start server?

The LM Studio shortcut for start server is lms server start on Windows or lms server start on Mac. Start the local LM Studio API server (CLI).

What is the LM Studio shortcut for creativity (0–1)?

The LM Studio shortcut for creativity (0–1) is Temperature on Windows or Temperature on Mac. Higher = more creative, lower = more deterministic.

How do I use keyboard shortcuts in LM Studio?

To use keyboard shortcuts in LM Studio, simply press the key combination while the application is focused. Most shortcuts work immediately without any additional setup. On Mac, replace Ctrl with Cmd and Alt with Option for most shortcuts.

How many keyboard shortcuts does LM Studio have?

LM Studio has 22 keyboard shortcuts across 3 categories on shortcut-tools.com. These cover all major features and workflows.

← All Shortcuts

LM Studio Keyboard Shortcuts & Commands (5)

5 LM Studio shortcuts and commands.

About LM Studio

LM Studio is a popular AI tool used by professionals worldwide. Learning keyboard shortcuts can dramatically speed up your workflow — studies show shortcut users save an average of 8 days per year compared to mouse-only users.

This page covers all 22 LM Studio shortcuts across 3 categories: UI Shortcuts, Server & API, Model Parameters. Each shortcut includes a description to help you understand when and how to use it effectively.

💡 Pro Tips for LM Studio Users

Start with the essentials: Learn Ctrl + N (New chat) and Ctrl + Shift + N (New window) first — these are the most commonly used.

Practice daily: Pick 2–3 new shortcuts each day and consciously use them instead of the mouse. Within a week, they become muscle memory.

Print this cheat sheet: Keep a reference nearby until shortcuts become automatic. Focus on the UI Shortcuts category first.

AI workflow tip: Combine keyboard shortcuts with prompt templates to create a fast, repeatable workflow. Save your best prompts and trigger them instantly.

Related Shortcut Pages

ChatGPT OpenAI Codex CLI OpenClaw Claude Code Gemini Midjourney

Search all shortcuts interactively

Open Shortcut Finder

All Shortcuts

UI Shortcuts

Shortcut	Action	Description
`Ctrl` + `N`	New chat	Start a new conversation.
`Ctrl` + `Shift` + `N`	New window	Open a new LM Studio window.
`Ctrl` + `,`	Settings	Open application settings.
`Ctrl` + `Enter`	Send message	Send the current message.
`Shift` + `Enter`	New line	Insert a line break without sending.
`Ctrl` + `K`	Clear chat	Clear the current chat history.
`Ctrl` + `F`	Find models	Search available models in the browser.
`Ctrl` + `D`	Model details	View details of the selected model.

Server & API

Shortcut	Action	Description
`lms server start`	Start server	Start the local LM Studio API server (CLI).
`lms server stop`	Stop server	Stop the running API server.
`lms server status`	Server status	Check whether the server is running.
`lms ls`	List models	List all downloaded models via CLI.
`lms load <model>`	Load model	Load a specific model into memory.
`lms unload`	Unload model	Unload the currently active model.
`GET` / `v1` / `models`	List models (API)	OpenAI-compatible endpoint to list loaded models.
`POST` / `v1` / `chat` / `completions`	Chat API	OpenAI-compatible chat completions endpoint.
`POST` / `v1` / `completions`	Completion API	OpenAI-compatible text completion endpoint.

Model Parameters

Shortcut	Action	Description
`Temperature`	Creativity (0–1)	Higher = more creative, lower = more deterministic.
`Context Length`	Token window	Max tokens for input + output combined.
`Top P`	Nucleus sampling	Probability mass threshold for token selection.
`Repeat Penalty`	Avoid repetition	Penalise recently used tokens to reduce repetition.
`GPU Layers`	GPU offload	Number of model layers to offload to GPU.