Google has already started the process of letting companies self-host Gemini, even on NVidia Blackwell GPUs.

Although imho, they really should bundle it with their TPUs as a turnkey solution for those clients who haven't invested in large scale infra like DCs yet.

▲

to11mtm 7 days ago | parent | next [-]

My guess is that either google want's a high level of physical control over their TPUs, or they have one sort of deal or another with NVidia and don't want to step on their toes.

And also, Google's track record with hardware.

▲

ActorNightly 6 days ago | parent | prev [-]

Its the same format as other software - you release the actual software for free but offer managed services that work with that software way better and easier.

	▲	fakedang 5 days ago \| parent [-]
		Yeah but those are on Google's managed cloud, and not onprem. But that recent announcement has been specifically for Google Distributed Cloud, which is huge. My point was a bit more specific though. To elaborate, I know of a number of publicly traded companies (USD $200M+ market cap) globally which have identified use cases for onprem AI and want to implement them actively but cannot, because they lack the knowhow to work with onprem, and hiring talent to implement that is just extremely expensive. Google should simply provide it as a turnkey bundle and milk them for it.