Trending storyDeveloping
Janus local LLM server appears
1 report1 sourceupdated 2 hours ago
What happened
AI digest
On October 2, 2026, the Hacker News front page covered Janus, a local large model server. It ships as a single Go binary and runs GGUF models through llama.cpp's Vulkan backend, working with AMD, Intel and NVIDIA GPUs as well as CPU. For access, Janus offers an OpenAI-compatible API and a built-in web UI. The coverage discloses its single-program form, model backend, hardware support and access methods.
Written by AI from the coverage · updated 48 minutes ago
Coverage
Follow the reports to see the story from different sides.
Oct 2
- Hacker News front pageShow HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia
Janus 是单个 Go 二进制程序，可通过 llama.cpp 的 Vulkan 后端在 AMD、Intel、NVIDIA GPU 上运行 GGUF 模型，也支持 CPU，并提供 OpenAI 兼容 API 和内置 Web UI。
Heat over time
Not enough continuous observations to draw a trend yet.