Instructions to use ig1/Qwen3.5-9B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ig1/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="ig1/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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("ig1/Qwen3.5-9B-NVFP4")
model = AutoModelForImageTextToText.from_pretrained("ig1/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?"}
        ]
    },
]
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 ig1/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 "ig1/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": "ig1/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/ig1/Qwen3.5-9B-NVFP4

SGLang

How to use ig1/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 "ig1/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": "ig1/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 "ig1/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": "ig1/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 ig1/Qwen3.5-9B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/ig1/Qwen3.5-9B-NVFP4
```

ig1sa commited on Mar 30

Commit

e55d04c

verified ·

1 Parent(s): ca4a26c

Add files using upload-large-folder tool

Browse files

Files changed (1) hide show

docker-compose.yaml +65 -0

docker-compose.yaml ADDED Viewed

	@@ -0,0 +1,65 @@

+services:
+  qwen35-rp:
+    image: ghcr.io/iguanesolutions/qwen35-rp:v0.2.0
+    container_name: Qwen3.5-ReverseProxy
+    environment:
+      QWEN35RP_LOGLEVEL: INFO
+      QWEN35RP_ENFORCE_SAMPLING_PARAMS: "true"
+      QWEN35RP_TARGET: "http://vllm-qwen3.5-9b-nvfp4:8000"
+      QWEN35RP_SERVED_MODEL_NAME: "Qwen3.5-9B"
+      QWEN35RP_THINKING_GENERAL_MODEL: "Qwen3.5-9B Thinking General"
+      QWEN35RP_THINKING_CODING_MODEL: "Qwen3.5-9B Thinking Coding"
+      QWEN35RP_INSTRUCT_GENERAL_MODEL: "Qwen3.5-9B Instruct General"
+      QWEN35RP_INSTRUCT_REASONING_MODEL: "Qwen3.5-9B Instruct Creative"
+    ports:
+      - "127.0.0.1:8000:9000"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+    restart: unless-stopped
+  vllm-qwen3.5-9b-nvfp4:
+    image: vllm/vllm-openai:v0.18.0-cu130
+    container_name: Qwen3.5-9B-NVFP4-vLLM
+    command:
+      - "ig1/Qwen3.5-9B-NVFP4"
+      - --served-model-name
+      - "Qwen3.5-9B"
+      - --reasoning-parser
+      - "qwen3"
+      - --enable-auto-tool-choice
+      - --tool-call-parser
+      - "qwen3_coder"
+      - --max-model-len
+      - "auto"
+      - --limit-mm-per-prompt.video
+      - "0"
+      - --max-cudagraph-capture-size
+      - "64"
+      - --max-num-seqs
+      - "64"
+      - --gpu-memory-utilization
+      - "0.8"
+    environment:
+      HF_TOKEN: ${HF_TOKEN:-} # Uses env var if set, otherwise empty
+      VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS: "1"
+    runtime: nvidia
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    # ports:
+    #   - "127.0.0.1:8000:8000"
+    volumes:
+      - E:\cache:/root/.cache # Adapt to your host
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+    restart: unless-stopped