Instructions to use OpenVINO/Qwen2-VL-7B-Instruct-int4-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenVINO/Qwen2-VL-7B-Instruct-int4-ov with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="OpenVINO/Qwen2-VL-7B-Instruct-int4-ov")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("OpenVINO/Qwen2-VL-7B-Instruct-int4-ov")
model = AutoModelForImageTextToText.from_pretrained("OpenVINO/Qwen2-VL-7B-Instruct-int4-ov")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenVINO/Qwen2-VL-7B-Instruct-int4-ov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenVINO/Qwen2-VL-7B-Instruct-int4-ov"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenVINO/Qwen2-VL-7B-Instruct-int4-ov",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/OpenVINO/Qwen2-VL-7B-Instruct-int4-ov

SGLang

How to use OpenVINO/Qwen2-VL-7B-Instruct-int4-ov with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OpenVINO/Qwen2-VL-7B-Instruct-int4-ov" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenVINO/Qwen2-VL-7B-Instruct-int4-ov",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OpenVINO/Qwen2-VL-7B-Instruct-int4-ov" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenVINO/Qwen2-VL-7B-Instruct-int4-ov",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use OpenVINO/Qwen2-VL-7B-Instruct-int4-ov with Docker Model Runner:
```
docker model run hf.co/OpenVINO/Qwen2-VL-7B-Instruct-int4-ov
```

Qwen2-VL-7B-Instruct-int4-ov

Model creator: Qwen
Original model: Qwen/Qwen2-VL-7B-Instruct

Description

This is Qwen/Qwen2-VL-7B-Instruct model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT4 by NNCF.

Quantization Parameters

Weight compression was performed using nncf.compress_weights with the following parameters:

mode: INT4_ASYM

Compatibility

The provided OpenVINO™ IR model is compatible with:

OpenVINO version 2025.2.0 and higher
Optimum Intel 1.26.0 and higher

Running Model Inference with OpenVINO GenAI

Install packages required for using OpenVINO GenAI.

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

pip install huggingface_hub

Download model from HuggingFace Hub

import huggingface_hub as hf_hub

model_id = "OpenVINO/Qwen2-VL-7B-Instruct-int4-ov"
model_path = "Qwen2-VL-7B-Instruct-int4-ov"

hf_hub.snapshot_download(model_id, local_dir=model_path)

Run model inference:

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

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

def load_image(image_file):
    if isinstance(image_file, str) and (image_file.startswith("http") or image_file.startswith("https")):
        response = requests.get(image_file)
        image = Image.open(BytesIO(response.content)).convert("RGB")
    else:
        image = Image.open(image_file).convert("RGB")
    image_data = np.array(image.getdata()).reshape(1, image.size[1], image.size[0], 3).astype(np.byte)
    return ov.Tensor(image_data)

prompt = "What is unusual in this picture?"

url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"
image_tensor = load_image(url)

def streamer(subword: str) -> bool:
    print(subword, end="", flush=True)
    return False

pipe.start_chat()
output = pipe.generate(prompt, image=image_tensor, max_new_tokens=100, streamer=streamer)
pipe.finish_chat()

More GenAI usage examples can be found in OpenVINO GenAI library docs and samples

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under apache-2.0 license. More details can be found in original model card.

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.

Downloads last month: 132

Model tree for OpenVINO/Qwen2-VL-7B-Instruct-int4-ov

Base model

Qwen/Qwen2-VL-7B

Finetuned

Qwen/Qwen2-VL-7B-Instruct

Quantized

(59)

this model