LLMs-local
Curated list of platforms, engines, models and tools for running LLMs on your own machine
An awesome-style list of everything needed to run large language models locally: inference platforms such as LM Studio, Jan, LocalAI, ChatBox and lemonade, and engines such as ollama, llama.cpp, vLLM, exo and BitNet. Further sections cover user interfaces, models by purpose (general, coding, multimodal, image, audio), leaderboards and explorers, agent frameworks, MCP, RAG, coding agents, computer use, browser automation, memory, evaluation and observability, fine-tuning and hardware. It closes with tutorials on prompt and context engineering, inference and agents, plus links to communities. Useful if you would rather keep models on your own hardware than call an API.