EdgeAI.computer

Software provider

Hugging Face

Hosts open-weight models and publishes the SmolVLM family of compact vision-language models designed explicitly for on-device inference under the Apache 2.0 licence.

Visit website
New York, United StatesProfile reviewed editorially

Categories

Local AI Models
Developer Tools
On-Device AI

Industries served

Healthcare
Retail
Manufacturing

Solutions from Hugging Face

Small single-board computer with a camera module attached
Hugging Face

SmolVLM

Apache 2.0 compact vision-language model family, from 2 billion parameters down to a 256 million variant.

Parameters
2 billion flagship; 256 million compact variant
Licence
Apache 2.0
Modality
Vision-language (image and text input)
Deployment
Edge board, mobile device or small edge server
On-device image question answering
Camera scene description
Embedded multimodal features
View DetailsCompareWebsite

Company information is summarised from publicly available material. If you represent Hugging Face and would like to update or expand this profile, please get in touch.