Hugging Face makes it easier for devs to run AI models on third-party clouds


AI dev platform Hugging Face has partnered with third-party cloud vendors including SambaNova to launch Inference Providers, a feature designed to make it easier for devs on Hugging Face to run AI models using the infrastructure of their choice.

Other partners involved with the new effort include Fal, Replicate, and Together AI.

Hugging Face says its partners have worked with it to build access to their respective data centers for running models into Hugging Face’s platform. Now, developers on Hugging Face can, for example, spin up a DeepSeek model on SambaNova’s servers from a Hugging Face project page in just a few clicks.

Hugging Face has long offered its own in-house solution for running AI models. But in a blog post Tuesday, the company explained that its focus has shifted to collaboration, storage, and model distribution capabilities.

Inference provider options as they appear on Hugging Face project pages.Image Credits:Hugging Face

“Serverless providers have flourished, and the time was right for Hugging Face to offer easy and unified access to serverless inference through a set of great providers,” the company wrote in the post. “[I]t was natural to partner with the next generation of serverless inference providers for model-centric, serverless inference.”

Serverless inference lets developers deploy and scale AI models without configuring or managing any of the underlying hardware. Providers like SambaNova automatically launch the necessary computing resources and scale them up or down depending on usage.

Hugging Face says that developers who use third-party cloud providers through its platform will pay the standard provider API rates, at least for now. (Hugging Face may establish revenue-sharing agreements with provider partners in the future, it says.) All Hugging Face users get a small quota of credits to put toward inference, and subscribers to Hugging Face Pro, Hugging Face’s premium tier, get an additional $2 of credits a month.

Hugging Face Inference Providers
The settings menu for Inference Providers.Image Credits:Hugging Face

Founded in 2016 as a chatbot startup, Hugging Face has become one of the largest AI model hosting and development platforms globally. To date, Hugging Face has raised close to $400 million in capital from investors including Salesforce, Google, Amazon, and Nvidia. The company claims to be profitable.

Recent Articles

Related Stories

Leave A Reply

Please enter your comment!
Please enter your name here