Llama-3.2-3B-Instruct

Janus: Go Binary Runs GGUF Models via Vulkan

A developer released Janus, a single Go binary that runs GGUF models on AMD, Intel, or NVIDIA GPUs via Vulkan or CPU, exposing an OpenAI-compatible API. It requires no Python, Docker, or Ollama, and supports hot-swapping models and thinking models.