ProperlyProperTea

@ProperlyProperTea@lemmy.ml

This is a remote user, information on this page may be incomplete. View at Source ↗

⁨Comment⁩ on ⁨What I run on my $10 USD OpenStick, Linux, Homelab⁩ ⁨⁨11⁩ ⁨hours⁩ ago⁩:
One of the few silver linings of the rampocalypse that I’ve noticed is a small increase in programs being developed to use less memory.
⁨Comment⁩ on ⁨It's self hosting Sunday! What's up?⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:
Isn’t that only for YouTube?

But yes, something similar to that.
⁨Comment⁩ on ⁨It's self hosting Sunday! What's up?⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:
This reminds me of a project idea I’ve had.

Auto-muting a TV using an HDMI splitter and an SBC running some sort of algorithm that detects if there’s an ad on the TV.
⁨Comment⁩ on ⁨Is anyone self-hosting their own AI?⁩ ⁨⁨3⁩ ⁨weeks⁩ ago⁩:
Last night I managed to run Qwen Flash Next iq2 XS using Strata in docker on a VM

I passed through my 3090 64GB of DDR4 12 vcores of my 5960x

Managed 90t/s

I’ll probably try a larger version soon but QFN already seems a lot more capable than 3.6 35b A3B, and runs better than Qwen 3.8 dense in llama.cpp