Of course when outage strikes this service will also be down ...
( due to circumstances _absolutely nobody_ could foresee )
193 publicly visible posts • joined 22 Jun 2012
I recently dabbled with ollama on CPU only 64gb old cheap server loading for example Gemma3 37GB model for cpu infrrencing. It _is_ slow but say 10 minutes for complete answer is not eternity either.
From what I understand ollama can work hybrid, load as much to gpu vram as possible, and the rest to system RAM.
This way you could still use gpu, and models bigger than its VRAM
I am still noob, mind you
Tested on Ubuntu 22.04
I have a 2016 Lenovo laptop that I upgraded from Ubuntu Mate 20.04 to 22.04 only few weeks back . 24.04 will have to wait few more years and possibly another machine.
Yes , I got kernel panic after upgrade but it was easily resolvable, thank goodness :-) /my machine has Radeon/intel combo/
After all I only needed to replace ugly new icon set with beautiful classic set, maintained in some obscure github site, and now I am happy bunny !