in my case with a 6900xt:

1. sudo pacman -S ollama-rocm

2. ollama serve

3. ollama run deepseek-r1:32b

Does that entire model fit in gpu memory? How's it run?

I tried running a model larger than ram size and it loads some layers into the gpu but offloads to the cpu also. It's faster than cpu alone for me, but not by a lot.

you're right, actually noticed gpu clocking up and down with 32b, 14b clocks up fully and actually runs faster

Nice, last time I tried out ROCm on Arch a few years ago it was a nightmare. Glad to see it's just one package install away these days, assuming you didn't do any setup beforehand.

I think you do still have to have the ROCm drivers installed, but it's not very hard to do from AMD's website.

everything from arch repos, well cachyos and arch :)

Anaconda also has committed engineering resources to assist with the no-GIL transition.

You can also use https://github.com/SimonBrazell/privacy-redirect to auto redirect from twitter to nitter

Oooh this is great, thank you. I've been wanting to set up something like this for quite a while and haven't really spent the time to figure out how I'd do it. Glad to have an option just land on my screen like this! Cheers :)

Also just realized there are one or two other services they could redirect (e.g. Medium -> scribe.rip). Will see if it's feasible for them to easily add...

See https://gitlab.gnome.org/GNOME/gnome-shell/-/issues/4665

Will this finallly motivate Zoom to use proper Pipewire API so that screen capture works on Wayland KDE?

https://github.com/EnixCoda/Gitako + https://github.com/sindresorhus/refined-github