ggml-org/Llama-macOS

Health v2 · maintenance only

Adoption not part of the score

1472 stars · 101 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A native macOS menu bar app for running local LLMs, built on llama.cpp by the GGML org. It exposes an OpenAI-compatible local server at localhost:9931, manages GGUF model installation from Hugging Face, and auto-configures models for your Mac's hardware.

Use cases

• run local llms on my mac
• chat with local models without sending data to the cloud
• serve an openai-compatible api for local models
• install gguf models from hugging face easily
• connect coding agents to a local llm server
• auto-unload idle models to save memory

When to choose

• you want a zero-config, fully local LLM runtime on macOS
• you want a tiny native app that shares the llama.cpp/Hugging Face model cache
• you need an OpenAI-compatible endpoint for other tools and agents

When to avoid

• you need LLM serving on Linux or Windows
• you want multi-GPU or datacenter-scale inference
• you need a cross-platform GUI for local models

Facets

application · maturity active

llm-inference http-server chat-interface gui large-language-models artificial-intelligence self-hosted developer-tools menu-bar-app local-llm gguf llama-cpp openai-compatible-api hugging-face macos desktop swift

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ggml-org/Llama-macOS")