Changelog

Model pages now display hardware compatibility for MLX models. Logged-in users see compatibility indicators based on their configured hardware, with clear warnings when Apple Silicon is required.

This brings MLX in line with GGUF, helping you quickly identify which variants will run on your machine before downloading.

You can now sort models by their number of parameters on the https://huggingface.co/models page and on user and organization profiles. Two new sorting options are available: "Most parameters" and "Least parameters."

All Hugging Face Papers now include a built-in assistant, powered by HuggingChat and the Hugging Face MCP server. It helps you quickly understand papers by answering questions, summarizing key ideas, and providing context as you browse the latest research.

You can now set a primary organization on your profile to highlight your team affiliation across the Hub. Your org badge will appear next to your username, visible on your profile and activity.

You can set it from your profile page and update it from your profile settings anytime. Available for Team and Enterprise organizations.

All Hugging Face Docs pages now feature a built-in assistant in the bottom-right corner, powered by HuggingChat and the Hugging Face MCP server.

It's designed to help you find answers faster about Hugging Face libraries and services, giving you guidance and explanations right when you need them.