gemma3onmac.py

gemma3onmac.py

import torch
from transformers import pipeline

pipe = pipeline(
    "image-text-to-text",
    device="mps",
    model="google/gemma-3-12b-it" # "google/gemma-3-27b-it"
)


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?"}
        ]
    }
]

output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"][-1]["content"])