The question that decides everything
The Hub holds four kinds of thing, and beginners lose days by reaching for the wrong one. A creative person who wants forty photographs cut out downloads a 7 GB model and installs Python for two days. A developer who needs a background job run nightly opens a browser app and clicks four hundred times. Both are working hard in the wrong place.
The four shelves
Models are weights plus configuration. A model is inert. It does nothing until some code loads it, so a model page is a parts bin, not a tool.
Datasets are the data — text, images, audio, labels — with an automatic preview table and, for public datasets, an automatic conversion to a queryable format. Lesson eight is about using them without downloading them.
Spaces are running applications. Someone has written the code, listed the dependencies and pointed it at a model, and the Hub runs it on a URL. This is the shelf that matters most if you do not write code, and lessons four and five are about it.
Inference is somebody else's hardware running a model for you over an API. Two shapes:
- Inference Providers route your request out to partner companies — the roster has included Together, Fireworks, Replicate, Groq, Cerebras, SambaNova and others, and it changes. One API key reaches many models, and you pay per token or per image. Free accounts get a small monthly credit; a PRO subscription, around nine dollars a month as of late 2025, raises it. Check current prices rather than trusting that figure.
- Inference Endpoints are a dedicated container on a GPU you rent by the hour. Right when you need consistent latency or isolation, wrong for occasional use, because it bills while idle unless you configure it to scale to zero.
Choosing, in one pass
- You want a job done a handful of times, on your own files, today → a Space.
- You want the same job done four hundred times, on a schedule → a provider API, or a script running the model locally.
- The material must not leave your machine — client photographs, medical notes, a customer's confidential documents → local, and nothing else. This is not a preference. Uploading is a disclosure.
- You want to show a colleague, or change how the tool behaves → duplicate a Space.
- You want to train or fine-tune → a dataset plus a GPU, which does not have to be a paid one. Kaggle notebooks give roughly thirty GPU-hours a week free once you verify a phone number, and Google Colab's free tier gives a smaller, interruptible allocation. Both are real options if a rented GPU is out of reach.
The part nobody mentions about public Spaces
A public Space is arbitrary code, written by a stranger, running on a machine you do not control, and whatever you upload passes through it. Most authors are decent and most Spaces are thin wrappers around a model. But the honest position is that you cannot know, and the thing that makes the Hub unusual is that you can go and look: the Files tab of a Space shows app.py. Read it. It is normally under two hundred lines.
For anything sensitive, duplicate the Space into your own account so the code runs under your control, or run the model locally. The next two lessons cover the first; lesson seven covers the second.
Do this now
Take the task actually in front of you and say out loud which of the four shelves it belongs on, and why the other three are wrong. If the answer is *local because the files are confidential*, skip ahead to lesson seven before you upload anything.
Before you move on