Custom Swift and Metal runtime enabling 26B instruction-tuned model inference in around 2 GB RAM by streaming weights from SSD, optimized for Apple Silicon Macs.

Custom Swift and Metal runtime enabling 26B instruction-tuned model inference in around 2 GB RAM by streaming weights from SSD, optimized for Apple Silicon Macs.

OpenRain is an OpenAI-compatible AI API gateway that lets developers access multiple major AI models through one API key and one unified endpoint.



Open-source AI platform for running LLMs entirely on your own infrastructure, with an OpenAI-compatible API, management dashboard, and zero data egress.
