Instructions to use Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound with Transformers:

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

pipe = pipeline("image-text-to-text", model="Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound")
model = AutoModelForMultimodalLM.from_pretrained("Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound", device_map="auto")
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 Settings

vLLM

How to use Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound",
		"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/Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound

SGLang

How to use Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound 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 "Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound" \
    --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": "Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound",
		"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 "Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound" \
        --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": "Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound",
		"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 Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound with Docker Model Runner:
```
docker model run hf.co/Intel/Qwen3.6-35B-A3B-int2-mixed-CT-AutoRound
```

Convert to OpenVINO

by savvadesogle - opened 18 days ago

Discussion

savvadesogle

18 days ago

Hello. Please tell me which library versions and which command are used to correctly convert to the OpenVINO format.

optimum-cli export openvino --model . --library transformers --trust-remote-code --task image-text-to-text Qwen3.6-35B-A3B-int2-mixed-AutoRound-LLMC-ov

Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Scripts\optimum-cli.exe\__main__.py", line 10, in <module>
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\commands\optimum_cli.py", line 219, in main
    service.run()
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\commands\export\openvino.py", line 469, in run
    main_export(
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\exporters\openvino\__main__.py", line 647, in main_export
    submodel_paths = export_from_model(
                     ^^^^^^^^^^^^^^^^^^
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\exporters\openvino\convert.py", line 839, in export_from_model
    export_models(
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\exporters\openvino\convert.py", line 486, in export_models
    export(
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\exporters\openvino\convert.py", line 235, in export
    return export_pytorch(
           ^^^^^^^^^^^^^^^
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\exporters\openvino\convert.py", line 332, in export_pytorch
    patcher = config.patch_model_for_export(model, model_kwargs=model_kwargs)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\exporters\openvino\model_configs.py", line 1786, in patch_model_for_export
    return self.patcher_cls(self, model, model_kwargs=model_kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\exporters\openvino\model_patcher.py", line 10275, in __init__
    super().__init__(config, model, model_kwargs)
  File "C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\optimum\exporters\openvino\model_patcher.py", line 9967, in __init__
    from transformers.models.qwen3_5.modeling_qwen3_5 import Qwen3_5DynamicCache
ImportError: cannot import name 'Qwen3_5DynamicCache' from 'transformers.models.qwen3_5.modeling_qwen3_5' (C:\Users\uuk\miniconda3\envs\openvino-latest\Lib\site-packages\transformers\models\qwen3_5\modeling_qwen3_5.py)

(openvino-latest)

wenhuach

Intel org 16 days ago

You may want to submit this issue directly to the OpenVINO repo, as your message here may not reach the right people. Our small team doesn’t have enough bandwidth to triage and forward these issues, as we mainly focus on the quantization process.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment