ggml-org/Llama-macOS
macOS menu bar app for running local LLMs
- Chart
- Not on a chart right now
- Stars
- 1.8k
What it is
Llama is a 4 MB native macOS menu bar app for running local LLMs on top of llama.cpp. It starts a local API server at localhost:9931/v1 and loads models on demand while unloading them when idle.
Who it is for
It is aimed at Mac users and developers who want to run local GGUF models for chat, coding agents, or other apps with minimal setup.
Why it is trending
It gained 76 stars today to reach 1,840 total stars following its 0.47.0 release on November 5, 2026. Developed by ggml-org alongside llama.cpp, it shares the Hugging Face cache and automatically configures models for the host Mac.
Main features
- Local OpenAI-compatible server with on-demand model loading and unloading
- Hardware-based model recommendations and one-click Hugging Face GGUF installs
- Automatic per-model configuration with overrides via models.user.ini
- Optional network access over Tailscale or local interfaces
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary