A new Hardware filter on the Models page filters results to models that fit a specific GPU, CPU, or Apple Silicon chip, so you only see what will actually run on your machine. Set the hardware you want from your [Hardware…
Hugging Face Changelog
Mon
Wed
Fri
JulAugSepOctNovDecJanFebMarAprMayJunJul
LessMore
Releases12Avg4/mo
You can now share your feedback on the Hub directly with the Hugging Face team from the user menu. Whether you want to report a bug, suggest a new feature, or share any other thoughts, your feedback will be carefully reviewed by the team to help shape future improvements.
Enterprise organizations can now create service accounts: dedicated, organization-owned identities for programmatic access such as CI/CD pipelines, automation scripts, and backend integrations. They aren't tied to any individual, so automated workflows keep running even as…
You can now publish to Hugging Face repositories from GitHub, GitLab, or custom CI systems without adding secrets, using workflow identity federation. This mirrors the secret-less Trusted Publishing experience available for npm and PyPI. CI jobs can also read from gated…
A new Base only toggle on the Models page hides every finetune, adapter, merge, and quantization, leaving just the original base models. The Other → Model Tree filter also provides the opposite, listing only one relation type across the Hub, like every adapter or every…
Copy the contents of any repository directly from the Hub to a Bucket using the new "Copy to Bucket" button on repository pages. Powered by Xet server-side transfers, large files are copied instantly, making it possible to transfer terabytes in just a few seconds. You can now…
Filter dataset benchmark leaderboards by the number of model parameters. On any dataset leaderboard, pick a size range and the rankings refresh to that bucket. The top 3 models in each size category are marked with a 🏅.
Every Gradio Space now auto-serves an /agents.md endpoint, a machine-readable API description that AI agents can read and call directly. Point your coding agents (like Claude Code, Codex, or Pi) at it and they figure out how to use the Space without any setup.
Kernels repositories provide an easy way to use kernels: precompiled, optimized for your exact hardware and PyTorch version, ready for torch.compile, and yields 1.7–2.5× speed-ups over baseline PyTorch. You can now browse and load Kernels from the Kernels Hub.
PRO users can now continue using ZeroGPU Spaces above their daily included quota. Over-quota usage requires purchasing pre-paid credits. The price is $1 per 10 minutes of over-quota ZeroGPU usage.
Upload traces from AI agents (Claude Code, Codex, Pi) directly to Hugging Face Datasets. The Hub auto-detects trace formats and tags datasets as Traces with a dedicated viewer for browsing sessions, turns, tool calls, and model responses. Upload JSONL files from local…
Mount HF Buckets as persistent storage volumes directly in Spaces. In Space settings, create or select a bucket, set the mount path and access mode. Also attach a bucket when creating a new Space. Useful for caching model weights, storing user uploads, or sharing files between…
Attach any Storage Bucket, model, or dataset from the Hub as a local filesystem. Allows attaching remote storage 100x bigger than local machine's disk—perfect for agentic storage. Read-write access for Storage Buckets, read-only for models and datasets. Install from GitHub:…
Set Spaces to protected, making them private on Hugging Face while keeping their URL publicly accessible. Useful for deploying production-ready demos or internal tools without exposing model weights, prompts, or proprietary logic. Can be combined with custom domains to host…
AI agents (Cursor, Claude Code) now receive Markdown versions of Hugging Face Papers automatically, saving tokens and improving efficiency. A new hugging-face-paper-pages skill for AI agents enables searching papers by title, author, or semantic similarity, reading content, and…
Last Checked
7d ago
Latest
Jun 30, 2026
Source
huggingface.co/changelog
