LLMTray icon

LLMTray

Local LLMs from your macOS menu bar — no terminal tab required.

Download for macOS ~1MB · macOS 13+ (Apple Silicon) · unsigned, right-click → Open on first launch View source on GitHub →
No Electron Swift / SwiftUI Apache 2.0
LLMTray's menu bar popover, showing a running server, model picker, and chat settings

What it does

Start/stop a local server

Runs a patched mlx_lm.server against any model in your models folder (~/.llmtray/models by default, or point it at LM Studio's).

Browse & download from Hugging Face

Search mlx-format models, download with a real progress bar — speed, ETA, pause/resume, and a size check per file.

Built-in chat

Streamed reasoning shown separately from the final answer, tok/s, adjustable temperature/top-p/max tokens.

Icon reflects real state

Green + pulsing while anything is generating — including an external tool hitting the server directly — orange/red under real thermal pressure.

Small, fast, no bloat

Native Swift/SwiftUI, no Electron, no bundled runtime. The whole app is a ~1MB download and sits idle at a few MB of memory until you actually start a server.

Quick start

  1. Download LLMTray.dmg and drag it to Applications.
  2. First launch: right-click the app → Open (clears Gatekeeper for this unsigned build).
  3. Click the brain icon in the menu bar and pick a model — the server starts on its own, every launch.

Building from source

For contributing, or if you'd rather not run an unsigned binary:

git clone https://github.com/ipsupport-llc/llmtray.git
cd llmtray
swift build
.build/debug/LLMTray