Llama.cpp now supports Vulkan, so it doesn't matter what card you're using.
SillySausage
I successfully ran local Llama with llama.cpp and an old AMD GPU. I'm not sure why you think there's no other option.
Have they released the hi-fi tier they promised years ago?
Between Tidal's high quality streaming and my Jellyfin server with FLAC of my CDs, I'm happy.
Here's a task for you: how do you convert a folder with 5000 images from png to jpg, while ensuring that they are scaled to at most 1024x768 and have a semi transparent watermark on them?
I know how to do it quickly using the command line, but have no idea how to do it with a GUI.
Why is Jared Leto hugging him?
Nice try, Nintendo, I will not buy your wares.
We need Canada in the European Song Contest.
I'd say we're deep in Farscape territory right now, heading for Lexx fast.
I could clearly... hear... both of them.
Want a nice project to spend your resources on? Try working on a PDF viewer that supports verifying signatures, form filling and signing documents.
Stop fucking around with meaningless issues.