from transformers import pipeline pipe = pipeline("image-text-to-text", model="unsloth/Qwen3.6-27B-NVFP4") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages) My static Space

Welcome to your static Space!

You can modify this app directly by editing index.html in the Files and versions tab.

Also don't forget to check the Spaces documentation.

from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("unsloth/Qwen3.6-27B-NVFP4") model = AutoModelForMultimodalLM.from_pretrained("unsloth/Qwen3.6-27B-NVFP4") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))