pip install -U "git+https://github.com/huggingface/optimum-intel.git" torchvision "Pillow" --extra-index-url https://download.pytorch.org/whl/cpu
pip install --pre -U openvino --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
pip install -U "transformers==5.2"

import requests
from PIL import Image
from transformers import AutoProcessor
from optimum.intel.openvino import OVModelForVisualCausalLM

model_id = "OpenVINO/Qwen3.5-35B-A3B-int4-ov"
processor = AutoProcessor.from_pretrained(model_id)
model = OVModelForVisualCausalLM.from_pretrained(model_id)

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
image = Image.open(requests.get(url, stream=True).raw)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=200)
print(processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0])

pip install huggingface_hub "Pillow"
pip install --pre -U openvino openvino-tokenizers openvino-genai --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly

import huggingface_hub as hf_hub

model_id = "OpenVINO/Qwen3.5-35B-A3B-int4-ov"
model_path = "Qwen3.5-35B-A3B-int4-ov"

hf_hub.snapshot_download(model_id, local_dir=model_path)

import numpy as np
import openvino as ov
import openvino_genai as ov_genai
import requests
from PIL import Image

device = "CPU"
pipe = ov_genai.VLMPipeline(model_path, device)

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
image_tensor = ov.Tensor(np.array(image)[None])

print(pipe.generate("Describe this image.", image=image_tensor, max_new_tokens=200))