I regret building a $3000 Pi AI Cluster

It’s been a while. Some Kickstarters take time.

What do you think about doing the same thing 10 times in a row, over and over? If that’s your jam, build a cluster like I did in this video!

If you want to replicate the Compute Blade Cluster, here are all the parts I used (some links are affiliate links):

– Compute Blade DEV:
– Compute Blade Standard Fan Unit:
– Compute Blade 10″ 3D Print Rackmount:
– Raspberry Pi CM5 16GB (CM5016000):
– GLOTRENDS Aluminum CM5 Heatsink:
– Patriot P300 256GB NVMe SSD 10-pack:
– GigaPlus 2.5 Gbps 10 port PoE+ switch:
– GigaPlus 10″ Rack Mount 3D Print ears:
– Monoprice Cat6A SlimRun 6″ Cat6 patch cables (10 pack):
– ioplex SFP+ Twinax DAC patch cable:
– DeskPi RackMate TT:

Other resources mentioned in the video:

– My older Compute Blade video:
– Xerxes Pi Kickstarter:
– Xerxes Pi testing:
– Unredacted Labs’ Tor exit cluster:
– World’s Largest Pi Cluster at UC Santa Barbara:

Support me on Patreon:
Sponsor me on GitHub:
Merch:
2nd Channel:
3rd Channel:

Contents:

00:00 – 2 years 2 long
00:32 – Another blade
01:30 – Unboxing a cluster
03:06 – Assembling one of 10
06:11 – A bandolier of microSD cards
07:16 – Assembling blades 2-10
08:16 – Next steps – fans and storage
10:17 – Flashing NVMe drives
11:00 – Only Fan Units
12:45 – They all just… disappeared
14:33 – Spending another $200
15:45 – Cluster benchmarks: HPL
16:23 – Spending another $70
17:03 – Framework cluster vs Pi cluster
18:12 – AI clustering (down one node)
19:26 – llama.cpp is totally RPC
20:54 – Exo and Distributed Llama
22:09 – Blade (the movie) vs blade (the compute)