With the release of Ampere, NVIDIA was very late with rolling out a compatible driver stack to it partners. Everyone wants to push its cards out of the door as soon as possible, and this resulted in testing and quality assurance being mostly limited to power and voltage stability testing. Unlike with previous launches, NVIDIA's partners reportedly had less time to thoroughly test their designs.
One issue in particular seems to be that the cards that experience crash-to-desktop issues when hitting high frequencies use cheaper power regulation configurations. If this is the reason of the crashes, it appears NVIDIA's partners didn't make the right trade-off in terms of cost and performance.
NVIDIA in their Founders' Edition designs uses a hybrid capacitor deployment, with four SP-CAPs and two MLCC groups of 10 individual capacitors each in the center. MSI uses a single MLCC group in the central arrangement, with five SP-CAPs guaranteeing the rest of the cleanup duties. ZOTAC went the cheapest way (which may be one of the reasons their cards are also among the cheapest), with a six POSCAP design (which are worse than MLCCs, remember). ASUS, however, designed their TUF with six MLCC arrangements - there were no savings done in this power circuitry area.Via: TPU