Re:Darkbloom – Private inference on idle Macs
by TuringNYC on Thursday April 16, 2026 @12:53AM
(#47788781)
I'd love a way to do this locally -- pool all the PCs in our own office for in-office pools of compute. Any suggestions from anyone? We currently run ollama but manually manage the pools
[ Parent
| on HN ]
Re:Darkbloom – Private inference on idle Macs
by zozbot234 on Thursday April 16, 2026 @04:09AM
(#47790110)
If you set CPUSchedulingPolicy=idle Nice=19 IOSchedulingClass=idle in the ollama server configuration it should run in the background with lowest priority.
Re:Darkbloom – Private inference on idle Macs
by utopiah on Thursday April 16, 2026 @03:56AM
(#47790014)
Seems like so much more work than "just" paying for https://huggingface.co or whichever other neocloud who already did all the setup for you and just waits for your credit card per minute/seconds/token.
Re:Darkbloom – Private inference on idle Macs
by TuringNYC on Thursday April 16, 2026 @11:19AM
(#47794505)
It is much more work because for many workloads you have geographic ringfencing and cannot send it out to the cloud
Re:Darkbloom – Private inference on idle Macs
by utopiah on Friday April 17, 2026 @02:48AM
(#47803145)
Doubt this kind of workloads would agree to send data then to a cloud of randos devices, precisely when cloud providers to certify they aren't looking at clients data (Customer-managed encryption keys, CMEK).
Re:Darkbloom – Private inference on idle Macs
by TuringNYC on Saturday April 18, 2026 @11:18AM
(#47816586)
>> Doubt this kind of workloads would agree to send data then to a cloud of randos devices,
Totally agree, which is why i said "I'd love a way to do this locally -- pool all the PCs in our own office for in-office pools of compute."
Re:Darkbloom – Private inference on idle Macs
by damezumari on Thursday April 16, 2026 @01:00AM
(#47788816)