Alternatives to Llama

Local LLM server with GPU and NPU acceleration

Discover, download, and run local LLMs

Get up and running with large language models locally

Client for LLaMA models

LLM server built on MLX

Interact with Ollama models

Run LLMs locally

Menu bar customization tool

Desktop automation application

Desktop application for Open WebUI

Menu bar usage monitor for Codex and Claude

Run local AI models on Apple Silicon