Run with OpenVINO

OpenVINO Model Server serves the recommended models with an OpenAI-compatible API, and is recommended for supported hardware configurations, particularly Intel AI hardware. To use llama.cpp instead, see Run with llama.cpp.

Before you start

• Install the latest drivers for your Intel GPU.
• Install OpenVINO Model Server by following the OpenVINO Model Server documentation.

Start the server

Start OpenVINO Model Server with your chosen model, and note the address and port it listens on.

Keep the server running

The model server must keep running while you use Artemis Desktop.

Next step

Connect the model to Artemis Desktop, using the server's host and port as the Address.