How to load the model?
#5
by dfg543 - opened
I encountered this error when using both Ollama and Llama.cppunknown model architecture: 'qwen3vlmoe'
https://github.com/Thireus/llama.cpp/releases
You can try the builds here, with tags containing tr-qwen3-vl-3, note that this is only a test version.
dfg543 changed discussion status to closed