Qwen3-VL GGUF support
Qwen has uploaded many ggufs ,can you support it in comfyui
such as https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct-GGUF
it should work for text generation or image recognition; if you want to use it as text encoder, you should refer to the specific model (image/video)'s config
I want to know how we can use the gguf in python.They don't provide an example
it's very simple; if you have gguf-connector (gguf node's engine) installed, you could just execute ggc gpp then select the gguf model file to interact with (see below)
for example, ask the model (i.e., Qwen3-VL-4B-Instruct-GGUF you provided above) what is gguf-connector? you might be able to see this output
or you could opt ggc cpp for model interaction with basic GUI
please check [gguf-connector] (https://pypi.org/project/gguf-connector/) for details
Just like llama , what i want is python code like llama-cpp-python, so we can use it in comfyui or other platform.