I have a server running in my basement with 2 nvidia Tesla GPUs that I bought for ~$70 each on ebay. (Unfortunately the RAM cost an arm and a leg). I built it for inference, but I also set it up to run sunshine server and now I have my Steam library on the TV through a Raspberry Pi 3. Even better, it was a fun and interesting project, maybe not as straightforward as you think. Unfortunately it's entirely possible that it costs .24/hr just for the electricity.

Now, this feels fine with <10ms input latency over wifi. Even in 2026 I'm skeptical about sending my input to Atlanta and back.

▲

swiftcoder 2 hours ago | parent [-]

> Unfortunately it's entirely possible that it costs .24/hr just for the electricity

Of course you don't need 2x teslas just to stream a game to your living room - a relatively power-efficient streaming box is possible

▲

wildzzz an hour ago | parent | next [-]

The raspberry pi is the actual device hooked up to the TV I think, the GPUs are elsewhere in the house.

▲

TiredOfLife an hour ago | parent | prev [-]

The game runs on that pc in basement

	▲	swiftcoder an hour ago \| parent [-]
		Yes, I understand that. My point is that 2x Teslas are overkill for gaming - his power bill is so high because he's using an expensive ML inference box to stream games.