Support for Qwen 3.5 models

[DomDXD]

I'm trying to load a very small GGUF model using llama-cpp-python and it's not working. The AI Opus tried to build from code and it's failing because if a CMAKE issue. This this wrapper works at all with the new Qwen3.5 models?

Thanks

[gezerman]

You can also use llama-server to host your model locally and send requests for chat completion-it doesn't yet support new qwen models