Llama
macOS menu bar app for running local LLMs via a local server.
Tested on macOS
Use it
macOS arm64
Install Llama via brew cask
mkdir -p ~/Applications ~/pickfit-out && brew install --cask --appdir=$HOME/Applications llama-app
Open Llama from Applications; it runs in the menu bar.
What it does
- Chat with models in the built-in web interfaceNot tested
- Install GGUF models from Hugging FaceNot shown working
- Connect other apps or use the API directlyNot tested
How far pickfit got
macOS arm64
- Installs
- Opens
- 0 of 3 features work
- Works offline
Good for
- chat with a model in the built-in WebUI
- install GGUF models from Hugging Face
- connect coding agents and editors via API
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
macOS arm64
It opens to its main screen
- Replayed from scratch
- Checked on 1 Nov 2026
- Version 0.46.1
When pickfit opened it, its main screen rendered. That shows it installs and starts; pickfit did not use any of its features. The launch passed again with the network off.
Differences the test machine hit
- README: brew install --cask llama-app
In the test: brew install --cask --appdir=$HOME/Applications llama-app with mkdir -p ~/Applications - README: Start Llama runs local server
In the test: Menu-bar app shows no dock window; pickfit clicked menu-bar item to open 300x412 menu window - README: Install any GGUF from Hugging Face in one click
In the test: Point tiny local GGUFs via ~/.config/llama/models.user.ini [local/...] model=/Users/sbx/models/...gguf to avoid 241MB catalog download; server then lists them