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

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
```

SaylorTwift HF Staff commited on Mar 16

Commit

31cd3f0

verified ·

1 Parent(s): ef9cf3c

Add evaluation results from Step 3.5 Flash paper

Browse files

- HLE (text only): 23.1
- GPQA Diamond: 83.5
- MMLU-Pro: 84.4
- SWE-Bench Verified: 74.4%
- Terminal-Bench 2.0: 51.0%

Source: https://arxiv.org/abs/2602.10604 (Table 5, Vanilla inference)

Files changed (5) hide show

.eval_results/gpqa_diamond.yaml +9 -0
.eval_results/hle.yaml +10 -0
.eval_results/mmlu_pro.yaml +9 -0
.eval_results/swe_bench_verified.yaml +9 -0
.eval_results/terminal_bench_2.yaml +9 -0

.eval_results/gpqa_diamond.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 83.5
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift

.eval_results/hle.yaml ADDED Viewed

	@@ -0,0 +1,10 @@

+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 23.1
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift
+  notes: "Text Only"

.eval_results/mmlu_pro.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: TIGER-Lab/MMLU-Pro
+    task_id: mmlu_pro
+  value: 84.4
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift

.eval_results/swe_bench_verified.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: SWE-bench/SWE-bench_Verified
+    task_id: swe_bench_%_resolved
+  value: 74.4
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift

.eval_results/terminal_bench_2.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: harborframework/terminal-bench-2.0
+    task_id: terminalbench_2
+  value: 51.0
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift