Instructions to use FastFlowLM/Qwen3.5-4B-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FastFlowLM/Qwen3.5-4B-NPU2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="FastFlowLM/Qwen3.5-4B-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 AutoModel
model = AutoModel.from_pretrained("FastFlowLM/Qwen3.5-4B-NPU2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FastFlowLM/Qwen3.5-4B-NPU2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FastFlowLM/Qwen3.5-4B-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/Qwen3.5-4B-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/Qwen3.5-4B-NPU2

SGLang

How to use FastFlowLM/Qwen3.5-4B-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/Qwen3.5-4B-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/Qwen3.5-4B-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/Qwen3.5-4B-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/Qwen3.5-4B-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/Qwen3.5-4B-NPU2 with Docker Model Runner:
```
docker model run hf.co/FastFlowLM/Qwen3.5-4B-NPU2
```

Qwen3.5-4B-NPU2

Commit History

feat: update config

44ba3c2

FastFlowLM commited on Jul 9

feat: real q80

84cfa4d

FastFlowLM commited on Jul 9

refactor: update version

d6db6f7

ngdxzy commited on May 24

fix: fix template

9295508

ngdxzy commited on May 24

feat: add vision to lfs

de3bda8

ngdxzy commited on Mar 19

Update README.md

0c83c21
verified

FastFlowLM commited on Mar 17

Create README.md

7156e0b
verified

FastFlowLM commited on Mar 17

Update config.json

0df8d6f
verified

FastFlowLM commited on Mar 17

Update config.json (#2)

dc3b89e

FastFlowLM

Shouyu-joel commited on Mar 16

feat: add attribute

891c6d8

ngdxzy commited on Mar 16

feat: add flm version tag

df88c7e

ngdxzy commited on Mar 14

feat: enable image

0a5ed30

ngdxzy commited on Mar 14

feat: reorder cpu alpha/beta

76c09e9

ngdxzy commited on Mar 13

feat: add alpha/beta for prefill

2c205c9

ngdxzy commited on Mar 13

feat: add vision weight

68ac9b5

ngdxzy commited on Mar 13

tmp: dump README from Qwen

442c38a

ngdxzy commited on Mar 13

init: upload weights

ebf65d3

ngdxzy commited on Mar 13

initial commit

0a1e210
verified

FastFlowLM commited on Mar 13

Commit History

feat: update config 44ba3c2

feat: real q80 84cfa4d

refactor: update version d6db6f7

fix: fix template 9295508

feat: add vision to lfs de3bda8

Update README.md 0c83c21 verified

Create README.md 7156e0b verified

Update config.json 0df8d6f verified

Update config.json (#2) dc3b89e

feat: add attribute 891c6d8

feat: add flm version tag df88c7e

feat: enable image 0a5ed30

feat: reorder cpu alpha/beta 76c09e9

feat: add alpha/beta for prefill 2c205c9

feat: add vision weight 68ac9b5

tmp: dump README from Qwen 442c38a

init: upload weights ebf65d3

initial commit 0a1e210 verified

feat: update config

44ba3c2

feat: real q80

84cfa4d

refactor: update version

d6db6f7

fix: fix template

9295508

feat: add vision to lfs

de3bda8

Update README.md

0c83c21
verified

Create README.md

7156e0b
verified

Update config.json

0df8d6f
verified

Update config.json (#2)

dc3b89e

feat: add attribute

891c6d8

feat: add flm version tag

df88c7e

feat: enable image

0a5ed30

feat: reorder cpu alpha/beta

76c09e9

feat: add alpha/beta for prefill

2c205c9

feat: add vision weight

68ac9b5

tmp: dump README from Qwen

442c38a

init: upload weights

ebf65d3

initial commit

0a1e210
verified