Hugging Face
Collaborate on, discover, and host machine learning models, datasets, and applications.
More in APIs
See allWhat is Hugging Face?
Hugging Face is a machine learning collaboration platform for hosting and sharing public models, datasets, and applications. It supports multiple modalities, including text, images, video, audio, and 3D, and offers tools for model access, deployment, inference, and team collaboration.
Key features
Enables users to host and collaborate on unlimited public models, datasets, and applications.
Deploys machine learning models on dedicated and autoscaling infrastructure directly from the hub.
Provides access to over 45,000 models from AI providers through a single unified API without service fees.
Supports training new vocabularies and tokenizing text using pre-built tokenizer implementations.
Connect securely to an identity provider using Single Sign-On (SSO) integration.
Latest from the Hugging Face blog
- Nov 13, 2026Build a Robot Pick-and-Place Simulation with SimReady AssetsRead
- Nov 13, 2026XYBench: Helping with the problem behind the questionRead
- Nov 13, 2026llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystemRead
- Nov 12, 2026LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8BRead
- Nov 12, 2026The Definitive Fine-Tuning Guide for 3D Generation ModelsRead