Promote Sign in Sign up

Multimodal model

Step-3.7-Flash-NVFP4

Listed for image text to text. Explore the model card for usage and requirements.

stepfun-ai Multimodal Open weights apache-2.0
Open model card ↗
Type
Multimodal
Weights
Open
Downloads
282k
Likes
64
Pipeline
image text to text
License
apache-2.0

Model hub

stepfun-ai/Step-3.7-Flash-NVFP4

Repo
stepfun-ai/Step-3.7-Flash-NVFP4
Library
transformers
Access
Public
Technical tags and languages
en transformers safetensors step3p7 image-text-to-text vision-language multimodal moe conversational custom_code endpoints_compatible 8-bit modelopt
Open on Hugging Face

More from stepfun-ai

1