[question] local ollama models support?

[eisneim]

can i use qwen3-vl 30b with ollama running locally?

[Tongyu-Yan]

from langchain_ollama import ChatOllama
Yes you can! I haven't added that to the config file, but you can edit the main.py file and the config file where I set up the llm to do this. Use the ChatOllama package from langchain.

The action space in this repo is not what qwen3-vl was trained for, so you might constantly fail. I would suggest you to use our API in our API platform. Plenty of free credits are available now!

[Tongyu-Yan]

Ollama is supported.

[hotwa]

Does qwen3.5 support？