hwdsl2/docker-ollama

InferCrate: self-hosted local LLM server powered by Ollama. Secure by default with auto-generated Bearer token auth. Native Ollama API and an OpenAI-compatible /v1 API subset. First-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Docker deployment on CPU (amd64/arm64) or CUDA (amd64).

2 best points · 0 comments · 2 Hacker News posts · 11 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Secure-by-default Ollama Docker image with built-in auth, only ~70MB (2 points, 0 comments, by hwdsl2, 2026-04-30)
• Show HN: Secure-by-default Ollama Docker image with built-in auth, only 70MB (1 points, 0 comments, by hwdsl2, 2026-05-01)