Instructions to use stepfun-ai/Step-3.5-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/Step-3.5-Flash with Transformers:

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

pipe = pipeline("text-generation", model="stepfun-ai/Step-3.5-Flash", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("stepfun-ai/Step-3.5-Flash", trust_remote_code=True, dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stepfun-ai/Step-3.5-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/Step-3.5-Flash"
# 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-3.5-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stepfun-ai/Step-3.5-Flash

SGLang

How to use stepfun-ai/Step-3.5-Flash 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-3.5-Flash" \
    --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-3.5-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-3.5-Flash" \
        --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-3.5-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stepfun-ai/Step-3.5-Flash with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/Step-3.5-Flash
```

WinstonDeng commited on Feb 1

Commit

7b9aa10

verified ·

1 Parent(s): 09ce794

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ base_model:
 <div align="center">
 <div align="center" style="display: flex; justify-content: center; align-items: center;">
-  <img src="https://huggingface.co/stepfun-ai/Step-3.5-Flash/blob/main/stepfun.svg" width="25" style="margin-right: 10px;"/>
   <h1 style="margin: 0; border-bottom: none;">Step-3.5-Flash</h1>
 </div>
@@ -38,7 +38,7 @@ base_model:
 Step 3.5 Flash delivers performance parity with leading closed-source systems while remaining open and efficient.
-![]
 Performance of Step 3.5 Flash measured across **Reasoning**, **Coding**, and **Agency**. Open-source models (left) are sorted by their total parameter count, while top-tier proprietary models are shown on the right. xbench-DeepSearch scores are sourced from [official publications](https://xbench.org/agi/aisearch) for consistency. The shadowed bars represent the enhanced performance of Step 3.5 Flash using [Parallel Thinking](https://arxiv.org/pdf/2601.05593).
@@ -219,6 +219,8 @@ pip install "sglang[all] @ git+https://github.com/sgl-project/sglang.git"
 ```
 2. Launch the server.
   - For bf16 model
 SGLANG_ENABLE_SPEC_V2=1
 python3 -m sglang.launch_server \

 <div align="center">
 <div align="center" style="display: flex; justify-content: center; align-items: center;">
+  <img src="https://github.com/stepfun-ai/Step-3.5-Flash/blob/main/assets/stepfun.svg" width="25" style="margin-right: 10px;"/>
   <h1 style="margin: 0; border-bottom: none;">Step-3.5-Flash</h1>
 </div>
 Step 3.5 Flash delivers performance parity with leading closed-source systems while remaining open and efficient.
+![](https://github.com/stepfun-ai/Step-3.5-Flash/blob/main/assets/step-bar-chart.png)
 Performance of Step 3.5 Flash measured across **Reasoning**, **Coding**, and **Agency**. Open-source models (left) are sorted by their total parameter count, while top-tier proprietary models are shown on the right. xbench-DeepSearch scores are sourced from [official publications](https://xbench.org/agi/aisearch) for consistency. The shadowed bars represent the enhanced performance of Step 3.5 Flash using [Parallel Thinking](https://arxiv.org/pdf/2601.05593).
 ```
 2. Launch the server.
+```bash
   - For bf16 model
 SGLANG_ENABLE_SPEC_V2=1
 python3 -m sglang.launch_server \