Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia
Summary
Janus is a Go-based local LLM runner with Vulkan-backed model execution for GGUF models, exposing an OpenAI-compatible API and a built-in web UI. It aims to run models locally without Python or Docker, with optional Ollama support and hot-swap model loading.