awesome-local-llm

Why we included this project

Running LLMs on your own hardware usually means digging through dozens of GitHub pages to find the right engine, model, and supporting tools. This curated index collects the useful parts of that ecosystem in one place, with sections for inference platforms and engines, user interfaces, models, agent frameworks, RAG tooling, hardware, and tutorials. The model listings are split by workload, so you can quickly find a general-purpose, coding, multimodal, or audio model to start from. It also links to tutorials and community spaces, which helps when you are new to quantization, context engineering, or on-device inference. Use it to shortlist candidates, then check the individual projects against your own hardware and privacy constraints.