Although true, transistor count is only tangentially related to performance

It's certainly not the sole determinant of performance but given two reasonably solid designs, one with a vastly larger transistor budget and major node advantage to boot, I know which one I'd pick as likely winner.

Cache size is very related to performance.

That counts memory, right?

No, but it does include cache; the M1 Ultra should have 96MB of cache (>6B transistors) while Nvidia GPUs have relatively little cache. 128GB of DRAM has 1 trillion transistors.