Qwen3.5-9B-int8-ov

• Model creator: Qwen
• Original model: Qwen3.5-9B

Description

This is Qwen3.5-9B model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT8 by NNCF.

The model includes openvino_mtp_model.xml for built-in Multi-Token Prediction (MTP) speculative decoding.

Quantization Parameters

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

• mode: INT8_ASYM
• group_size: -1

For more information on quantization, check the OpenVINO model optimization guide.

Compatibility

The provided OpenVINO™ IR model is compatible with:

• OpenVINO version 2026.4.0 and higher
• OpenVINO GenAI 2026.4.0.0 and higher
• Optimum Intel 1.27.0 and higher

Running Model Inference with Optimum Intel

1. Install packages required for using Optimum Intel integration with the OpenVINO backend:

pip install -U "git+https://github.com/huggingface/optimum-intel.git" torchvision Pillow --extra-index-url https://download.pytorch.org/whl/cpu
pip install -U "openvino==2026.4.0"
pip install -U "transformers==5.2.0"

2. Run model inference:

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

model_id = "OpenVINO/Qwen3.5-9B-int8-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])

For more examples and possible optimizations, refer to the Inference with Optimum Intel.

Running Model Inference with OpenVINO GenAI

1. Install packages required for using OpenVINO GenAI.

pip install huggingface_hub "Pillow"
pip install -U "openvino==2026.4.0" "openvino-tokenizers==2026.4.0.0" "openvino-genai==2026.4.0.0"

2. Download model from HuggingFace Hub

import huggingface_hub as hf_hub

model_id = "OpenVINO/Qwen3.5-9B-int8-ov"
model_path = "Qwen3.5-9B-int8-ov"

hf_hub.snapshot_download(model_id, local_dir=model_path)

3. Run model inference:

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

device = "CPU"
scheduler_config = ov_genai.SchedulerConfig()
scheduler_config.enable_prefix_caching = False
draft = ov_genai.draft_model(model_path, device)
pipe = ov_genai.VLMPipeline(
    model_path,
    device,
    draft_model=draft,
    scheduler_config=scheduler_config,
)

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])

generation_config = ov_genai.GenerationConfig()
generation_config.max_new_tokens = 200
generation_config.do_sample = False
generation_config.num_return_sequences = 1
generation_config.num_assistant_tokens = 2

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

OpenVINO GenAI currently supports this MTP path with greedy decoding and prefix caching disabled, as demonstrated in the Qwen3.8 MTP notebook.

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

You can find more detailed usage examples in OpenVINO Notebooks:

• Qwen3-VL multimodal chatbot
• Visual-language assistant

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under Apache License Version 2.0 license. More details can be found in Qwen3.5-9B.

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.