

0·
24 days agoIf you have a lot of RAM, you can run small models slowly on the CPU. Your integrated graphics I would guess won’t fit anything useful in it’s vram, so if you really want to run something locally, getting some extra sticks of RAM is probably your cheapest option.
I have 64G and I run 8-14b models. 32b is pushing it (it’s just really slow)
I use it to auto update nginx and haproxy containers, since they adhere very well to semver there is very little risk of breakage if you use the correct tag and not just :latest. I haven’t had a single issue in many years, and it’s nice to know that I’ll get critical security updates within 24h of images being pushed.