Dictly
Hold a hotkey, speak, and get the text pasted or copied, transcribed on your Mac by Whisper.GetMIT
Llama
A small menu bar app from the ggml project that downloads GGUF models and serves them through a local OpenAI-style API.
MIT · Free download · Downloads from github.com
- License
- MIT
- Open source
- Source
- GitHub
- ggml-org
- Verified
- 2026
About Llama
Llama is a menu bar front end for llama.cpp, published by the ggml organisation. It starts a local server with an OpenAI-compatible API, recommends models that fit your Mac's memory, installs GGUF models from Hugging Face and loads them only when a request arrives, unloading them again when idle. A built-in web chat is included, and other apps, editors or coding agents can connect to the local endpoint.
If llama.cpp is already installed it is used, otherwise the app downloads a prebuilt binary; models are kept in the standard Hugging Face cache so other tools can share them. Per-model settings can be overridden in a user configuration file.
The server listens only on your Mac by default. Settings can expose it over Tailscale or to the whole local network; it has no password, so the project advises using the network option only on networks you trust. The app's build targets Apple silicon Macs running macOS 15 or later.
Information
- Source code
- ggml-org/Llama-macOS
- License
- MIT
- Website
- llama.app
- Download
- github.com
- Homebrew
- llama-app
- Category
- AI
- Alternative to
- LM Studio
- Topics
- Local AI apps, Menu bar apps
- Evidence checked
- Tags
OpenMacApps links to each project’s official download. Check its release notes for macOS version and Apple silicon support. The verification date records our license and source review, not a security audit.
Sources and image credits
- github.com/ggml-org/Llama-macOS
- github.com/ggml-org/Llama-macOS/blob/main/LICENSE
- github.com/ggml-org/Llama-macOS/blob/main/Llama.xcodeproj/project.pbxproj
- github.com/ggml-org/Llama-macOS/releases
- icon.png: Llama contributors (ggml-org). MIT; upstream project asset, trademarks retained.
License and artwork notices
For the Developer
Link to this page from your README with a badge.
[](https://openmacapps.com/apps/llama/)You Might Also Like
FlowDown
A native AI chat client for Mac, iPhone and iPad that works with local MLX models or OpenAI-compatible providers.GetAGPL-3.0
FluidVoice
A dictation app that turns speech into text in any app, using on-device speech models and optional AI cleanup.GetGPL-3.0
Jan
A desktop workspace for chatting with local models and supported remote AI services.GetApache-2.0
KeyType
System-wide tab autocomplete for macOS that suggests the next few words with a local language model.GetMIT
macai
A native macOS chat client for ChatGPT, Claude, Gemini, Grok, Ollama and other OpenAI-compatible AI services.GetApache-2.0
Nativ
A Mac workspace for chatting with, serving and monitoring local MLX models on Apple silicon.GetMIT
Ollama
Run supported language models on your Mac with a desktop app and local API.GetMIT
OpenSuperWhisper
Hotkey dictation for Apple silicon Macs that transcribes speech on-device with Whisper or Parakeet models.GetMIT
OpenUsage
A menu bar app that shows how much of your AI coding plans you have used, with limits, credits and reset times per account.GetMIT
OpenVoiceFlow
Push-to-talk dictation that transcribes on device with Whisper and pastes the text into whichever app you are using.GetAGPL-3.0+
Saga Reader
Collect articles on topics you choose and have a cloud or local language model summarise and discuss them with you.GetMIT