Instructions to use AxionML/Qwen3.5-9B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AxionML/Qwen3.5-9B-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="AxionML/Qwen3.5-9B-NVFP4")
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("AxionML/Qwen3.5-9B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("AxionML/Qwen3.5-9B-NVFP4", 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 AxionML/Qwen3.5-9B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AxionML/Qwen3.5-9B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AxionML/Qwen3.5-9B-NVFP4",
		"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/AxionML/Qwen3.5-9B-NVFP4

SGLang

How to use AxionML/Qwen3.5-9B-NVFP4 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 "AxionML/Qwen3.5-9B-NVFP4" \
    --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": "AxionML/Qwen3.5-9B-NVFP4",
		"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 "AxionML/Qwen3.5-9B-NVFP4" \
        --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": "AxionML/Qwen3.5-9B-NVFP4",
		"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 AxionML/Qwen3.5-9B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/AxionML/Qwen3.5-9B-NVFP4
```

Qwen3.5-9B-NVFP4

File size: 1,892 Bytes

0a723a5

{
    "producer": {
        "name": "modelopt",
        "version": "0.0.1.dev1+g82f1d216d"
    },
    "quantization": {
        "quant_algo": "NVFP4",
        "kv_cache_quant_algo": null,
        "group_size": 16,
        "exclude_modules": [
            "lm_head",
            "model.language_model.layers.0.linear_attn.conv1d",
            "model.language_model.layers.1.linear_attn.conv1d",
            "model.language_model.layers.10.linear_attn.conv1d",
            "model.language_model.layers.12.linear_attn.conv1d",
            "model.language_model.layers.13.linear_attn.conv1d",
            "model.language_model.layers.14.linear_attn.conv1d",
            "model.language_model.layers.16.linear_attn.conv1d",
            "model.language_model.layers.17.linear_attn.conv1d",
            "model.language_model.layers.18.linear_attn.conv1d",
            "model.language_model.layers.2.linear_attn.conv1d",
            "model.language_model.layers.20.linear_attn.conv1d",
            "model.language_model.layers.21.linear_attn.conv1d",
            "model.language_model.layers.22.linear_attn.conv1d",
            "model.language_model.layers.24.linear_attn.conv1d",
            "model.language_model.layers.25.linear_attn.conv1d",
            "model.language_model.layers.26.linear_attn.conv1d",
            "model.language_model.layers.28.linear_attn.conv1d",
            "model.language_model.layers.29.linear_attn.conv1d",
            "model.language_model.layers.30.linear_attn.conv1d",
            "model.language_model.layers.4.linear_attn.conv1d",
            "model.language_model.layers.5.linear_attn.conv1d",
            "model.language_model.layers.6.linear_attn.conv1d",
            "model.language_model.layers.8.linear_attn.conv1d",
            "model.language_model.layers.9.linear_attn.conv1d",
            "model.visual*",
            "mtp.layers.0*"
        ]
    }
}