noonghunna

noonghunna maintains club-3090, an open-source community project providing recipes and Docker Compose configs for serving large language models locally on consumer NVIDIA GPUs. The project ships verified multi-engine configs (vLLM, llama.cpp, SGLang, and more), benchmark data, and tooling to get an OpenAI-compatible API running on RTX 3090s and similar hardware with a single command. Development is community-driven, with contributors submitting benchmark results, patches, and new model configs via GitHub.