Model Hosting & Inference

Fast, scalable inference infrastructure for AI models

Open-source framework for shipping ML models to production

Fast, cheap inference for open-source models

Managed infrastructure for deploying and scaling Hugging Face models.

Serverless GPU cloud for Python AI workloads

Run open-source AI models in the cloud via a simple API

GPU cloud marketplace for AI training and inference

Fast inference cloud for LLaMA, Mistral, and Stable Diffusion