Qwen3-VL-30B-A3B-Instruct-int4-AutoRound

from transformers import Qwen3VLMoeForConditionalGeneration, AutoProcessor

# default: Load the model on the available device(s)
model_name = "Intel/Qwen3-VL-30B-A3B-Instruct-int4-AutoRound"
model = Qwen3VLMoeForConditionalGeneration.from_pretrained(
    model_name, dtype="auto", device_map="auto"
)

processor = AutoProcessor.from_pretrained(model_name)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Preparation for inference
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)
"""
This is a heartwarming and serene photograph capturing a moment of connection between a woman and her dog on a beach at sunset.
\n\nThe image is taken from a side angle, focusing on the interaction between the two subjects. A woman with long, dark hair is sitting on the sand,
turned towards a large, light-colored dog, likely a yellow Labrador Retriever. The dog is sitting upright and is actively engaging with the woman,
extending its right front paw to give her a "high five." The woman is smiling warmly, looking at the dog with affection as she reciprocates the gesture.
\n\nThe setting is a sandy beach with gentle
"""