Instructions to use stepfun-ai/Step-3.7-Flash-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/Step-3.7-Flash-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="stepfun-ai/Step-3.7-Flash-NVFP4", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("stepfun-ai/Step-3.7-Flash-NVFP4", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use stepfun-ai/Step-3.7-Flash-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/Step-3.7-Flash-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": "stepfun-ai/Step-3.7-Flash-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/stepfun-ai/Step-3.7-Flash-NVFP4

SGLang

How to use stepfun-ai/Step-3.7-Flash-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 "stepfun-ai/Step-3.7-Flash-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": "stepfun-ai/Step-3.7-Flash-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 "stepfun-ai/Step-3.7-Flash-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": "stepfun-ai/Step-3.7-Flash-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 stepfun-ai/Step-3.7-Flash-NVFP4 with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/Step-3.7-Flash-NVFP4
```

Step-3.7-Flash-NVFP4

Commit History

Update README.md

36afbf6
verified

mh3467 commited on about 10 hours ago

Remove sibling repo links (Collection sidebar covers this)

f4aeff5

mh3467 commited on about 17 hours ago

Fix repo name casing in SGLang FP8 example

b1d0d62

mh3467 commited on about 17 hours ago

Add benchmark chart referenced in README

1212b30

mh3467 commited on about 17 hours ago

Update README.md

c2f5d72
verified

WinstonDeng commited on about 20 hours ago

Sync Step3.7 remote code and processor config

4e84267

huangyu-nv commited on 1 day ago

Fix Step3.7 RoPE config compatibility

1584e8c
verified

huangyu-nv commited on 1 day ago

Upload Step3.7 NVFP4 checkpoint from step3p7-nvfp4-moe-only-mix_nvidia-calib4096-kvfp8

d8c9009
verified

huangyu-nv commited on 2 days ago

initial commit

30612ab
verified

WinstonDeng commited on 2 days ago

Commit History

Update README.md 36afbf6 verified

Remove sibling repo links (Collection sidebar covers this) f4aeff5

Fix repo name casing in SGLang FP8 example b1d0d62

Add benchmark chart referenced in README 1212b30

Update README.md c2f5d72 verified

Sync Step3.7 remote code and processor config 4e84267

Fix Step3.7 RoPE config compatibility 1584e8c verified

Upload Step3.7 NVFP4 checkpoint from step3p7-nvfp4-moe-only-mix_nvidia-calib4096-kvfp8 d8c9009 verified

initial commit 30612ab verified

Update README.md

36afbf6
verified

Remove sibling repo links (Collection sidebar covers this)

f4aeff5

Fix repo name casing in SGLang FP8 example

b1d0d62

Add benchmark chart referenced in README

1212b30

Update README.md

c2f5d72
verified

Sync Step3.7 remote code and processor config

4e84267

Fix Step3.7 RoPE config compatibility

1584e8c
verified

Upload Step3.7 NVFP4 checkpoint from step3p7-nvfp4-moe-only-mix_nvidia-calib4096-kvfp8

d8c9009
verified

initial commit

30612ab
verified