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_config.json

openvino-ci

Upload folder using huggingface_hub

0585c4e verified 4 days ago

raw

history blame contribute delete

2.7 kB

	{
	"dtype": "int4_int8_int8",
	"input_info": null,
	"optimum_version": "2.1.0.dev0",
	"output_attentions": false,
	"quantization_config": {
	"_dataset_kwargs": {},
	"dataset": null,
	"default_config": null,
	"ignored_scope": null,
	"num_samples": null,
	"processor": "/nfs/ov-share-01/data/cv_bench_cache/NATIVE_GEN-AI_MODELS/qwen3.5-35b-a3b/pytorch/NATIVE",
	"quantization_configs": {
	"lm_model": {
	"_dataset_kwargs": {},
	"all_layers": null,
	"backup_precision": null,
	"bits": 4,
	"dataset": null,
	"dq_group_size": null,
	"dtype": "int4",
	"gptq": null,
	"group_size": 128,
	"group_size_fallback": null,
	"ignored_scope": {
	"patterns": [
	".shared_expert.",
	".attn."
	]
	},
	"lora_correction": null,
	"num_samples": null,
	"processor": null,
	"quant_method": "default",
	"ratio": 1.0,
	"scale_estimation": null,
	"sensitivity_metric": null,
	"statistics_path": null,
	"sym": false,
	"tokenizer": null
	},
	"text_embeddings_model": {
	"_dataset_kwargs": {},
	"all_layers": null,
	"backup_precision": null,
	"bits": 8,
	"dataset": null,
	"dq_group_size": null,
	"dtype": "int8",
	"gptq": null,
	"group_size": null,
	"group_size_fallback": null,
	"ignored_scope": null,
	"lora_correction": null,
	"num_samples": null,
	"processor": null,
	"quant_method": "default",
	"ratio": 1.0,
	"scale_estimation": null,
	"sensitivity_metric": null,
	"statistics_path": null,
	"sym": true,
	"tokenizer": null,
	"weight_only": true
	},
	"vision_embeddings_merger_model": {
	"_dataset_kwargs": {},
	"all_layers": null,
	"backup_precision": null,
	"bits": 8,
	"dataset": null,
	"dq_group_size": null,
	"dtype": "int8",
	"gptq": null,
	"group_size": null,
	"group_size_fallback": null,
	"ignored_scope": null,
	"lora_correction": null,
	"num_samples": null,
	"processor": null,
	"quant_method": "default",
	"ratio": 1.0,
	"scale_estimation": null,
	"sensitivity_metric": null,
	"statistics_path": null,
	"sym": true,
	"tokenizer": null,
	"weight_only": true
	}
	},
	"tokenizer": "/nfs/ov-share-01/data/cv_bench_cache/NATIVE_GEN-AI_MODELS/qwen3.5-35b-a3b/pytorch/NATIVE"
	},
	"save_onnx_model": false,
	"transformers_version": "5.2.0"
	}