Instructions to use FastFlowLM/Qwen3.5-9B-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FastFlowLM/Qwen3.5-9B-NPU2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="FastFlowLM/Qwen3.5-9B-NPU2")
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 AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("FastFlowLM/Qwen3.5-9B-NPU2")
model = AutoModelForMultimodalLM.from_pretrained("FastFlowLM/Qwen3.5-9B-NPU2", 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 = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FastFlowLM/Qwen3.5-9B-NPU2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FastFlowLM/Qwen3.5-9B-NPU2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FastFlowLM/Qwen3.5-9B-NPU2",
		"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/FastFlowLM/Qwen3.5-9B-NPU2

SGLang

How to use FastFlowLM/Qwen3.5-9B-NPU2 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 "FastFlowLM/Qwen3.5-9B-NPU2" \
    --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": "FastFlowLM/Qwen3.5-9B-NPU2",
		"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 "FastFlowLM/Qwen3.5-9B-NPU2" \
        --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": "FastFlowLM/Qwen3.5-9B-NPU2",
		"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 FastFlowLM/Qwen3.5-9B-NPU2 with Docker Model Runner:
```
docker model run hf.co/FastFlowLM/Qwen3.5-9B-NPU2
```

FastFlowLM commited on Jul 9

Commit

eb89ce7

1 Parent(s): b41885f

feat: real q80

Browse files

Files changed (2) hide show

config.json +1 -1
model.q4nx +2 -2

config.json CHANGED Viewed

@@ -79,7 +79,7 @@
     },
     "addr_qk": 53248,
     "addr_kv": 53536,
-    "flm_version": "0.9.43",
     "vision_model_weight": "vision_weight.q4nx",
     "vision_end_token_id": 248054,
     "vision_start_token_id": 248053,

     },
     "addr_qk": 53248,
     "addr_kv": 53536,
+    "flm_version": "0.9.45",
     "vision_model_weight": "vision_weight.q4nx",
     "vision_end_token_id": 248054,
     "vision_start_token_id": 248053,

model.q4nx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fff5d9c85fbd99f14b497d58fd8fed1951701cbddd75e6fd19ae5269c164b14e
-size 7900055760

 version https://git-lfs.github.com/spec/v1
+oid sha256:723eb522214d7b242c108ccaf4be95a8a5c421e3bb55159d8a5b47816bff824d
+size 7632668880