• 0 Posts
  • 32 Comments
Joined 6 months ago
cake
Cake day: October 20th, 2025

help-circle








  • Interesting. I’d actually pay for an in browser VPN, it’s handy to be able to switch countries on the fly. Ideally even per browser tab.

    I would not however pay for Mozilla’s mullvad thing. I don’t like mullvad since they dropped port forwarding and OpenVPN. I use proton now for that. But in the browser is a different usecase for me.

    It’s just weird that it’s not possible to pay for this but only for the thing I don’t want.











  • Thank you so much!! I have been putting it off because what I have works but a time will soon come when I’ll want to test new models.

    I’m looking for a server but not many parallel calls because I would like to use as much context as I can. When making space for e.g. 4 threads, the context is split and thus 4x as small. With llama 3.1 8b I managed to get 47104 context on the 16GB card (though actually using that much is pretty slow). That’s with KV quant to 8b too. But sometimes I just need that much.

    I’ve never tried the llama.cpp directly, thanks for the tip!

    Kobold sounds good too but I have some scripts talking to it directly. I’ll read up on that too see if it can do that. I don’t have time now but I’ll do it in the coming days. Thank you!