This dataset is large, over 1 GB.
It's a correct use of a comma, yes.
I'll add something that's a little jarring about it as a sentence--which is how it might sound out in a person's head--especially if that person doesn't translate "1 GB" to "a gigabyte" automatically in their head.
You wouldn't write the following, but imagine it sounding like: This dataset is large, over one gee bee.
So your sentence could be smoother written as how you'd say it out loud:
- "This dataset is large--over a gigabyte."
Which is something you might prefer. But if you're talking about something larger, like 350 GB, then you'd certainly want to keep it as a number instead of expanding it out to "three-hundred-and-fifty gigabytes" (for instance).