Instructions to use OpenVINO/Qwen3.5-35B-A3B-int4-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenVINO/Qwen3.5-35B-A3B-int4-ov with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenVINO/Qwen3.5-35B-A3B-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, AutoModelForMultimodalLM

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

vLLM

How to use OpenVINO/Qwen3.5-35B-A3B-int4-ov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenVINO/Qwen3.5-35B-A3B-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/Qwen3.5-35B-A3B-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/Qwen3.5-35B-A3B-int4-ov

SGLang

How to use OpenVINO/Qwen3.5-35B-A3B-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/Qwen3.5-35B-A3B-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/Qwen3.5-35B-A3B-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/Qwen3.5-35B-A3B-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/Qwen3.5-35B-A3B-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/Qwen3.5-35B-A3B-int4-ov with Docker Model Runner:
```
docker model run hf.co/OpenVINO/Qwen3.5-35B-A3B-int4-ov
```

Qwen3.5-35B-A3B-int4-ov / openvino_vision_embeddings_model.xml

openvino-ci

Upload folder using huggingface_hub

0585c4e verified 25 days ago

raw

history blame contribute delete

5.16 kB

	<?xml version="1.0"?>
	<net name="Model63" version="11">
	<layers>
	<layer id="0" name="hidden_states" type="Parameter" version="opset1">
	<data shape="?,?" element_type="f32" />
	<output>
	<port id="0" precision="FP32" names="hidden_states">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="1" name="Constant_378170" type="Const" version="opset1">
	<data element_type="i64" shape="5" offset="0" size="40" />
	<output>
	<port id="0" precision="I64">
	<dim>5</dim>
	</port>
	</output>
	</layer>
	<layer id="2" name="aten::view/Reshape" type="Reshape" version="opset1">
	<data special_zero="false" />
	<input>
	<port id="0" precision="FP32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I64">
	<dim>5</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="FP32" names="14,9,hidden_states_1,input">
	<dim>-1</dim>
	<dim>3</dim>
	<dim>2</dim>
	<dim>16</dim>
	<dim>16</dim>
	</port>
	</output>
	</layer>
	<layer id="3" name="self.proj.weight" type="Const" version="opset1">
	<data element_type="f32" shape="1152, 3, 2, 16, 16" offset="40" size="7077888" />
	<output>
	<port id="0" precision="FP32" names="self.proj.weight">
	<dim>1152</dim>
	<dim>3</dim>
	<dim>2</dim>
	<dim>16</dim>
	<dim>16</dim>
	</port>
	</output>
	</layer>
	<layer id="4" name="__module.proj/aten::_convolution/Convolution" type="Convolution" version="opset1">
	<data strides="2, 16, 16" dilations="1, 1, 1" pads_begin="0, 0, 0" pads_end="0, 0, 0" auto_pad="explicit" />
	<input>
	<port id="0" precision="FP32">
	<dim>-1</dim>
	<dim>3</dim>
	<dim>2</dim>
	<dim>16</dim>
	<dim>16</dim>
	</port>
	<port id="1" precision="FP32">
	<dim>1152</dim>
	<dim>3</dim>
	<dim>2</dim>
	<dim>16</dim>
	<dim>16</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="FP32">
	<dim>-1</dim>
	<dim>1152</dim>
	<dim>1</dim>
	<dim>1</dim>
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="5" name="__module.proj/aten::_convolution/Reshape" type="Const" version="opset1">
	<data element_type="f32" shape="1, 1152, 1, 1, 1" offset="7077928" size="4608" />
	<output>
	<port id="0" precision="FP32">
	<dim>1</dim>
	<dim>1152</dim>
	<dim>1</dim>
	<dim>1</dim>
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="6" name="__module.proj/aten::_convolution/Add" type="Add" version="opset1">
	<data auto_broadcast="numpy" />
	<input>
	<port id="0" precision="FP32">
	<dim>-1</dim>
	<dim>1152</dim>
	<dim>1</dim>
	<dim>1</dim>
	<dim>1</dim>
	</port>
	<port id="1" precision="FP32">
	<dim>1</dim>
	<dim>1152</dim>
	<dim>1</dim>
	<dim>1</dim>
	<dim>1</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="FP32" names="33">
	<dim>-1</dim>
	<dim>1152</dim>
	<dim>1</dim>
	<dim>1</dim>
	<dim>1</dim>
	</port>
	</output>
	</layer>
	<layer id="7" name="Constant_378243" type="Const" version="opset1">
	<data element_type="i64" shape="2" offset="7082536" size="16" />
	<output>
	<port id="0" precision="I64">
	<dim>2</dim>
	</port>
	</output>
	</layer>
	<layer id="8" name="aten::view/Reshape_1" type="Reshape" version="opset1">
	<data special_zero="false" />
	<input>
	<port id="0" precision="FP32">
	<dim>-1</dim>
	<dim>1152</dim>
	<dim>1</dim>
	<dim>1</dim>
	<dim>1</dim>
	</port>
	<port id="1" precision="I64">
	<dim>2</dim>
	</port>
	</input>
	<output>
	<port id="2" precision="FP32" names="last_hidden_state">
	<dim>-1</dim>
	<dim>1152</dim>
	</port>
	</output>
	</layer>
	<layer id="9" name="Result_378271" type="Result" version="opset1" output_names="last_hidden_state">
	<input>
	<port id="0" precision="FP32">
	<dim>-1</dim>
	<dim>1152</dim>
	</port>
	</input>
	</layer>
	</layers>
	<edges>
	<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
	<edge from-layer="1" from-port="0" to-layer="2" to-port="1" />
	<edge from-layer="2" from-port="2" to-layer="4" to-port="0" />
	<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
	<edge from-layer="4" from-port="2" to-layer="6" to-port="0" />
	<edge from-layer="5" from-port="0" to-layer="6" to-port="1" />
	<edge from-layer="6" from-port="2" to-layer="8" to-port="0" />
	<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
	<edge from-layer="8" from-port="2" to-layer="9" to-port="0" />
	</edges>
	<rt_info>
	<info name="OpenVINO Runtime" value="2026.2.0-21894-5ec01181735-releases/2026/2" />
	<Runtime_version value="2026.2.0-21894-5ec01181735-releases/2026/2" />
	<conversion_parameters>
	<framework value="pytorch" />
	<is_python_object value="True" />
	</conversion_parameters>
	<optimum>
	<optimum_intel_version value="1.27.0.dev0+a8c4734" />
	<optimum_version value="2.1.0.dev0" />
	<pytorch_version value="2.11.0" />
	<transformers_version value="5.2.0" />
	</optimum>
	</rt_info>
	</net>