2
He is using
Qwen3.5 9B
download from the models in LM Studio
You can find other models to use at huggin face https://huggingface.co/models
3
Load Model in models, tab or chat tab, and check if model is working in chat
4
Make sure Developer Mode is on in settings, and also Enable Local LLM Studio so later we can use the server address in server tab in our python script