Step-3.7-Flash

Checkpointstepfun-ai/Step-3.7-FlashModel card indexedModel card

Support summary

Step-3.7-Flash is a checkpoint published by StepFun, built on the Step3p7ForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. Official recipes or cookbooks cover SGLang, without pinning a stable release.

vLLM documents support in 8 of 20 indexed releases, from 0.23.0 to 0.28.0.

Documented hardware
NVIDIA / CUDA
Documented quantization
BF16
Documented features
Multi-token prediction, Reasoning parsers, Speculative decoding, Tensor parallelism, and Tool calling
Configured context
262,144 tokens
License
apache-2.0

Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.

Hugging Face model card
Publisher
StepFun
Task
image text to text
License
apache-2.0
Library
transformers
Architecture
Step3p7ForConditionalGeneration
Weight tensor elements
201.4B
Tensor types
BF16, F32
Configured context
262,144 tokens
Languages
en
Weight access
Public
Repository created
2026-05-23
Source 1: stepfun-ai/Step-3.7-Flash · publisher model cardSource 2: stepfun-ai/Step-3.7-Flash · Hugging Face metadataSource 3: stepfun-ai/Step-3.7-Flash · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for Step-3.7-Flash
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedCheckpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed 0.28.0This release
Features, dependencies and evidence for vLLM 0.28.0
SGLangVersion not pinnedRecipe / cookbookDocumented recipe

Official recipe

Source 1: sglang · docs/cookbook/autoregressive/StepFun/Step-3.7-Flash.mdxSource 2: sglang · docs/src/snippets/autoregressive/step-37-flash-deployment.jsxReviewed
No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1

Recipes and cookbooks