See Willard Van Orman Quine, Confessions of a Confirmed Extensionalist and Other Essays (Dagfinn Follesdal editor, Harvard UP 2008), Ch.1 Nominalism (1946), page 11:
So nominalism is distinct from the doctrine known in modern logic as
extensionalism. The main point of the latter doctrine is rejection of properties,
or attributes, in favor of classes. But classes are universals equally
with attributes, and nominalism in the defined sense rejects both. The fact
that classes are universals is something obscured by calling them “mere aggregates”,
and feeling that this likens them to heaps, which are indeed particular.
A heap of stones is a particular, bigger than but no less particular
and concrete than any single stone which occurs in it as a part. But the
class of stones in the heap cannot be identified with the heap.
For, if it could, then by the same token the class of molecules of stones in the heap could be identified with the heap; and then there would be no
distinguishing between the two classes. This would be unacceptable, since
we want to say that the one class has some 150 members while the other
has some trillions.
In conclusion, regarding the sentence "Some students are brilliant", Quine would be committed to the existence of the class of brilliant things.
According to well-known Quinean criteria ("to be is to be a value of a variable"), to be committed to the existence of properties amounts to adopt second-order quantification. But for Quine [Philosophy of Logic, 1970], second-order logic is “set theory in sheep’s clothing”.