Scaleway, the new European Inference Provider on Hugging Face

Scaleway is now officially listed as an Inference Provider on the Hugging Face Hub.

Developers can directly select Scaleway to run serverless inference on models hosted on Hugging Face. They can choose between using Hugging Face’s routing or their own Scaleway API keys, which gives them more flexibility to test, benchmark, and deploy inference at scale.

Becoming an Inference Provider on Hugging Face means joining a global ecosystem where openness, flexibility, and performance are key. By integrating Scaleway, Hugging Face expands the range of providers available to its community, while giving developers the opportunity to run inference on a European cloud fully aligned with local standards and regulations.

“We are proud to enrich the Hugging Face ecosystem by giving developers a new opportunity to explore open, flexible, secure, and truly European cloud technology. This partnership is about broadening opportunities for the community while ensuring the highest standards of reliability and performance.”
— Damien Lucas, CEO of Scaleway

“With Scaleway, developers can now directly access the inference service of a major European cloud provider. This makes it easier than ever to try a provider compliant with European regulations, while still offering serverless inference for several high-quality open-weight models and expanding choice for the community.”
— Julien Chaumond, Co-founder & CTO of Hugging Face

👉 Find out more here