←back to thread

I regret building this $3000 Pi AI cluster

(www.jeffgeerling.com)
468 points speckx | 1 comments | 19 Sep 25 14:28 UTC | HN request time: 0s | source
Show context
Aurornis ◴[19 Sep 25 14:52 UTC] No.45302320[source]▶
I thought the conclusion should have been obvious: A cluster of Raspberry Pi units is an expensive nerd indulgence for fun, not an actual pathway to high performance compute. I don’t know if anyone building a Pi cluster actually goes into it thinking it’s going to be a cost effective endeavor, do they? Maybe this is just YouTube-style headline writing spilling over to the blog for the clicks.

If your goal is to play with or learn on a cluster of Linux machines, the cost effective way to do it is to buy a desktop consumer CPU, install a hypervisor, and create a lot of VMs. It’s not as satisfying as plugging cables into different Raspberry Pi units and connecting them all together if that’s your thing, but once you’re in the terminal the desktop CPU, RAM, and flexibility of the system will be appreciated.

replies(11): >>45302356 #>>45302424 #>>45302433 #>>45302531 #>>45302676 #>>45302770 #>>45303057 #>>45303061 #>>45303424 #>>45304502 #>>45304568 #
bunderbunder ◴[19 Sep 25 14:55 UTC] No.45302356[source]▶
The cost effective way to do it is in the cloud. Because there's a very good chance you'll learn everything you intended to learn and then get bored with it long before your cloud compute bill reaches the price of a desktop with even fairly modest specs for this purpose.
replies(12): >>45302408 #>>45302469 #>>45302503 #>>45302550 #>>45302742 #>>45302824 #>>45303327 #>>45303352 #>>45304169 #>>45304176 #>>45304278 #>>45305010 #
Almondsetat ◴[19 Sep 25 15:06 UTC] No.45302469[source]▶
I can get a Xeon E5-2690V4 with 28 threads and 64GB of RAM for about $150. If you need cores and memory to make a lot of VMs you can do it extremely cheaply
replies(7): >>45302491 #>>45302525 #>>45302535 #>>45302992 #>>45303342 #>>45303344 #>>45303461 #
nine_k ◴[19 Sep 25 15:09 UTC] No.45302491[source]▶
It will probably consume $150 worth of electricity in less than a month, even sitting idle :-\
replies(4): >>45302573 #>>45303255 #>>45303270 #>>45304285 #
blobbers ◴[19 Sep 25 15:15 UTC] No.45302573[source]▶
The internet says 100W idle, so maybe more like $40-50 electricity, depending on where you live could be cheaper could be more expensive.

Makes me wonder if I should unplug more stuff when on vacation.

replies(5): >>45302688 #>>45302709 #>>45302886 #>>45302909 #>>45306658 #
rogerrogerr ◴[19 Sep 25 15:42 UTC] No.45302886[source]▶
100W over a month (rule of thumb 730 hours) is 73kWh. Which is $7.30 at my $0.10/kWh rate, or less than $25 at (what Google told me is) Cali’s average $0.30/kWh.
replies(1): >>45303134 #
mercutio2 ◴[19 Sep 25 15:58 UTC] No.45303134[source]▶
Your googling gave results that were likely accurate for California 4-5 years ago. My average cost per kWh is about 60 cents.

Rates have gone up enormously because the cost of wildfires is falling on ratepayers, not the utility owners.

Regulated monopolies are pretty great, aren’t they? Heads I win, tales you lose.

replies(4): >>45303320 #>>45303324 #>>45303607 #>>45304654 #
LTL_FTC ◴[19 Sep 25 16:35 UTC] No.45303607[source]▶
They have definitely increased but not all of California is like this. In the heart of Silicon Valley, Santa Clara, it's about $0.15/kWh. Having Data Centers nearby helps, I suppose.
replies(2): >>45304593 #>>45305212 #
favorited ◴[19 Sep 25 19:06 UTC] No.45305212[source]▶
Santa Clara's energy rates are an outlier among neighboring municipalities, and should not be used as an example of energy cost in the Bay Area. Santa Clara residents are served by city-owned Silicon Valley Power, which has lower rates than PG&E or SVCE, which service almost all of the South Bay.
replies(1): >>45342527 #
1. LTL_FTC ◴[23 Sep 25 03:28 UTC] No.45342527[source]▶
Well the discussion was California as a whole and averages, so I decided to share. As with averages, data is above and bellow the mean, so when a commenter above said $.30/kwh was much too low for California, I decided to lend some support the the argument as I’m in California paying bellow the average. It’s a just a data point. A counter example to the claim made by parent. Maybe it helps fellow nerds pick a spot in the bay if they want to run their homelabs.