Alternatives to Swama

Get up and running with large language models locally

Discover, download, and run local LLMs

LLM server built on MLX

Interact with Ollama models

Run local AI models on Apple Silicon

Menu bar app for running local LLMs

Run LLMs locally

Inference engine for AI models

Client for LLaMA models

Virtual machines UI using QEMU

Run AI models locally across multiple devices

MCP client and inspector