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, AutoModelForImageTextToText

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

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_detokenizer.xml

openvino-ci

Upload folder using huggingface_hub

0585c4e verified 4 days ago

raw

history blame contribute delete

15.6 kB

	<?xml version="1.0"?>
	<net name="detokenizer" version="11">
	<layers>
	<layer id="0" name="Parameter_458775" type="Parameter" version="opset1">
	<data shape="?,?" element_type="i64" />
	<output>
	<port id="0" precision="I64" names="Parameter_458775">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="1" name="Convert_458810" type="Convert" version="opset1">
	<data destination_type="i32" />
	<input>
	<port id="0" precision="I64">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="1" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="2" name="Constant_458777" type="Const" version="opset1">
	<data element_type="i32" shape="248077" offset="0" size="992308" />
	<output>
	<port id="0" precision="I32">
	<dim>248077</dim>
	</port>
	</output>
	</layer>
	<layer id="3" name="Constant_458779" type="Const" version="opset1">
	<data element_type="i32" shape="248077" offset="992308" size="992308" />
	<output>
	<port id="0" precision="I32">
	<dim>248077</dim>
	</port>
	</output>
	</layer>
	<layer id="4" name="Constant_458781" type="Const" version="opset1">
	<data element_type="u8" shape="1843484" offset="1984616" size="1843484" />
	<output>
	<port id="0" precision="U8">
	<dim>1843484</dim>
	</port>
	</output>
	</layer>
	<layer id="5" name="Slice_458786" type="Const" version="opset1">
	<data element_type="i32" shape="21" offset="3828100" size="84" />
	<output>
	<port id="0" precision="I32">
	<dim>21</dim>
	</port>
	</output>
	</layer>
	<layer id="6" name="VocabDecoder_458788" type="VocabDecoder" version="extension">
	<data skip_tokens="" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>248077</dim>
	</port>
	<port id="2" precision="I32">
	<dim>248077</dim>
	</port>
	<port id="3" precision="U8">
	<dim>1843484</dim>
	</port>
	<port id="4" precision="I32">
	<dim>21</dim>
	</port>
	</input>
	<output>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="6" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="7" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="8" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="9" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="7" name="FuzeRagged_458789" type="FuzeRagged" version="extension">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="8" name="UTF8Validate_458790" type="UTF8Validate" version="extension">
	<data replace_mode="true" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="9" name="StringTensorPack_458791" type="StringTensorPack" version="opset15">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="STRING" names="Result_458792,string_output">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="10" name="Result_458792" type="Result" version="opset1" output_names="Result_458792,string_output">
	<input>
	<port id="0" precision="STRING">
	<dim>-1</dim>
	</port>
	</input>
	</layer>
	</layers>
	<edges>
	<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
	<edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
	<edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
	<edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
	<edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
	<edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
	<edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
	<edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
	<edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
	<edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
	<edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
	<edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
	<edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
	<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
	<edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
	<edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
	<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
	</edges>
	<rt_info>
	<info name="OpenVINO Runtime" value="2026.2.0-21894-5ec01181735-releases/2026/2" />
	<add_attention_mask value="True" />
	<add_prefix_space />
	<add_special_tokens value="True" />
	<chat_template value="{%- set image_count = namespace(value=0) %} {%- set video_count = namespace(value=0) %} {%- macro render_content(content, do_vision_count, is_system_content=false) %} {%- if content is string %} {{- content }} {%- elif content is iterable and content is not mapping %} {%- for item in content %} {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} {%- if is_system_content %} {{- raise_exception('System message cannot contain images.') }} {%- endif %} {%- if do_vision_count %} {%- set image_count.value = image_count.value + 1 %} {%- endif %} {%- if add_vision_id %} {{- 'Picture ' ~ image_count.value ~ ': ' }} {%- endif %} {{- '<\|vision_start\|><\|image_pad\|><\|vision_end\|>' }} {%- elif 'video' in item or item.type == 'video' %} {%- if is_system_content %} {{- raise_exception('System message cannot contain videos.') }} {%- endif %} {%- if do_vision_count %} {%- set video_count.value = video_count.value + 1 %} {%- endif %} {%- if add_vision_id %} {{- 'Video ' ~ video_count.value ~ ': ' }} {%- endif %} {{- '<\|vision_start\|><\|video_pad\|><\|vision_end\|>' }} {%- elif 'text' in item %} {{- item.text }} {%- else %} {{- raise_exception('Unexpected item type in content.') }} {%- endif %} {%- endfor %} {%- elif content is none or content is undefined %} {{- '' }} {%- else %} {{- raise_exception('Unexpected content type.') }} {%- endif %} {%- endmacro %} {%- if not messages %} {{- raise_exception('No messages provided.') }} {%- endif %} {%- if tools and tools is iterable and tools is not mapping %} {{- '<\|im_start\|>system\n' }} {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }} {%- for tool in tools %} {{- "\n" }} {{- tool \| tojson }} {%- endfor %} {{- "\n</tools>" }} {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }} {%- if messages[0].role == 'system' %} {%- set content = render_content(messages[0].content, false, true)\|trim %} {%- if content %} {{- '\n\n' + content }} {%- endif %} {%- endif %} {{- '<\|im_end\|>\n' }} {%- else %} {%- if messages[0].role == 'system' %} {%- set content = render_content(messages[0].content, false, true)\|trim %} {{- '<\|im_start\|>system\n' + content + '<\|im_end\|>\n' }} {%- endif %} {%- endif %} {%- set ns = namespace(multi_step_tool=true, last_query_index=messages\|length - 1) %} {%- for message in messages[::-1] %} {%- set index = (messages\|length - 1) - loop.index0 %} {%- if ns.multi_step_tool and message.role == "user" %} {%- set content = render_content(message.content, false)\|trim %} {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %} {%- set ns.multi_step_tool = false %} {%- set ns.last_query_index = index %} {%- endif %} {%- endif %} {%- endfor %} {%- if ns.multi_step_tool %} {{- raise_exception('No user query found in messages.') }} {%- endif %} {%- for message in messages %} {%- set content = render_content(message.content, true)\|trim %} {%- if message.role == "system" %} {%- if not loop.first %} {{- raise_exception('System message must be at the beginning.') }} {%- endif %} {%- elif message.role == "user" %} {{- '<\|im_start\|>' + message.role + '\n' + content + '<\|im_end\|>' + '\n' }} {%- elif message.role == "assistant" %} {%- set reasoning_content = '' %} {%- if message.reasoning_content is string %} {%- set reasoning_content = message.reasoning_content %} {%- else %} {%- if '</think>' in content %} {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %} {%- set content = content.split('</think>')[-1].lstrip('\n') %} {%- endif %} {%- endif %} {%- set reasoning_content = reasoning_content\|trim %} {%- if loop.index0 > ns.last_query_index %} {{- '<\|im_start\|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }} {%- else %} {{- '<\|im_start\|>' + message.role + '\n' + content }} {%- endif %} {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} {%- for tool_call in message.tool_calls %} {%- if tool_call.function is defined %} {%- set tool_call = tool_call.function %} {%- endif %} {%- if loop.first %} {%- if content\|trim %} {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }} {%- else %} {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }} {%- endif %} {%- else %} {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }} {%- endif %} {%- if tool_call.arguments is defined %} {%- for args_name, args_value in tool_call.arguments\|items %} {{- '<parameter=' + args_name + '>\n' }} {%- set args_value = args_value \| tojson \| safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value \| string %} {{- args_value }} {{- '\n</parameter>\n' }} {%- endfor %} {%- endif %} {{- '</function>\n</tool_call>' }} {%- endfor %} {%- endif %} {{- '<\|im_end\|>\n' }} {%- elif message.role == "tool" %} {%- if loop.previtem and loop.previtem.role != "tool" %} {{- '<\|im_start\|>user' }} {%- endif %} {{- '\n<tool_response>\n' }} {{- content }} {{- '\n</tool_response>' }} {%- if not loop.last and loop.nextitem.role != "tool" %} {{- '<\|im_end\|>\n' }} {%- elif loop.last %} {{- '<\|im_end\|>\n' }} {%- endif %} {%- else %} {{- raise_exception('Unexpected message role.') }} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<\|im_start\|>assistant\n' }} {%- if enable_thinking is defined and enable_thinking is false %} {{- '<think>\n\n</think>\n\n' }} {%- else %} {{- '<think>\n' }} {%- endif %} {%- endif %}" />
	<clean_up_tokenization_spaces />
	<detokenizer_input_type value="i64" />
	<eos_token_id value="248046" />
	<handle_special_tokens_with_re />
	<max_length />
	<number_of_inputs value="1" />
	<openvino_tokenizers_version value="2026.2.0.0-681-f43dbd55981" />
	<openvino_version value="2026.2.0-21894-5ec01181735-releases/2026/2" />
	<original_post_processor_template value="{"type": "ByteLevel", "add_prefix_space": false, "trim_offsets": false, "use_regex": false}" />
	<original_tokenizer_class value="<class 'transformers.tokenization_utils_tokenizers.TokenizersBackend'>" />
	<pad_token_id value="248044" />
	<processed_post_processor_template value="{"single": {"ids": [-1], "type_ids": [0]}, "pair": {"ids": [-1, -2], "type_ids": [0, 0]}}" />
	<sentencepiece_version value="0.2.1" />
	<skip_special_tokens value="True" />
	<streaming_detokenizer value="False" />
	<tiktoken_version value="0.12.0" />
	<tokenizer_output_type value="i64" />
	<tokenizers_version value="0.22.2" />
	<transformers_version value="5.2.0" />
	<use_max_padding value="False" />
	<use_sentencepiece_backend value="False" />
	<utf8_replace_mode value="replace" />
	<with_detokenizer value="True" />
	</rt_info>
	</net>