---
slug: lm-studio
kind: runbook
status: docs-checked
sh: https://insidethemachine.ai/install/lm-studio.sh
ps1: https://insidethemachine.ai/install/lm-studio.ps1
json: https://insidethemachine.ai/install/lm-studio.json
page: https://insidethemachine.ai/setups/lm-studio
---

# Install: LM Studio

Desktop app for discovering and running local models, plus the lms CLI and a local server.

**Run status: Not run: commands checked against the official docs only.** Commands checked against the official docs on 2026-10-15. Not run end to end.

**This script:** The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

## One command

```bash
curl -fsSL https://insidethemachine.ai/install/lm-studio.sh | bash
```

Windows (PowerShell):

```powershell
irm https://insidethemachine.ai/install/lm-studio.ps1 | iex
```

Actions: `| bash -s -- plan` (print only), `verify`, `rollback --yes`. Env: ITM_RAM. Read the script first: `curl -fsSL https://insidethemachine.ai/install/lm-studio.sh | less`.

Lines marked YOU RUN are not run by the script (servers, interactive apps, your own files). The script prints them at the end, in order.

## Steps

### macOS

Install:

1. **Install LM Studio**
   - run (macOS only): `brew install --cask lm-studio`
   - run: `npx lmstudio install-cli`
2. **Configure (your choices)**
   - YOU RUN (start the local API server): `lms server start`
   - YOU RUN (list downloaded models): `lms ls`

Verify:

- `lms status` → expect: shows LM Studio status
- `lms ls --json` → expect: machine-readable model list
- `curl -s http://localhost:1234/v1/models` → expect: JSON model list (1234 is LM Studio's usual server port; check the app if changed)

Rollback:

- run: `lms server stop`
- run (macOS only): `brew uninstall --cask lm-studio`
- note: downloaded models and settings live under ~/.lmstudio; delete only if you want them gone

### Linux

Install:

1. **Install LM Studio**
   - note: download the Linux build from https://lmstudio.ai/ then run: npx lmstudio install-cli
2. **Configure (your choices)**
   - YOU RUN (start the local API server): `lms server start`
   - YOU RUN (list downloaded models): `lms ls`

Verify:

- `lms status` → expect: shows LM Studio status
- `lms ls --json` → expect: machine-readable model list
- `curl -s http://localhost:1234/v1/models` → expect: JSON model list (1234 is LM Studio's usual server port; check the app if changed)

Rollback:

- run: `lms server stop`
- run (macOS only): `brew uninstall --cask lm-studio`
- note: downloaded models and settings live under ~/.lmstudio; delete only if you want them gone

### Windows (PowerShell, not run by us)

Install:

1. **Install LM Studio**
   - note: download the installer from https://lmstudio.ai/ then run: npx lmstudio install-cli

Verify:

- `lms status` → expect: shows LM Studio status
- `lms ls --json` → expect: machine-readable model list
- by hand: `curl -s http://localhost:1234/v1/models` → expect: JSON model list (1234 is LM Studio's usual server port; check the app if changed)

Rollback:

- run: `lms server stop`
- YOU RUN (macOS/Linux command; do the same by hand): `brew uninstall --cask lm-studio`
- YOU RUN (macOS/Linux command; do the same by hand): `# downloaded models and settings live under ~/.lmstudio; delete only if you want them gone`