miss_brainfarts
@miss_brainfarts@lemmy.blahaj.zone
- Comment on Steam summer sale is on now! What games do you recommend? 5 months ago:
Shadow of War is 90% off, that’s very much worth it
- Comment on conservation 8 months ago:
I’d watch hermit crabs for a first date, hell yeah.
- Comment on Star Citizen's first-person shooting is getting backpack-reloading, dynamic crosshairs, procedural recoil, and other improvements to 'bring the FPS combat to AAA standard' 9 months ago:
Procedural recoil? So basically, random recoil you can never learn the patterns for?
- Comment on Google gets its way, bakes a user-tracking ad platform directly into Chrome 10 months ago:
And nowadays, most online ads are intrusive and privacy-defeating tracking, so you know
- Comment on FLOSS communities right now 10 months ago:
So nice, right? Just being able to curate where your search engine pulls result from… I wish I’d discovered it sooner
- Comment on Mongolian. Like the barbecue. 10 months ago:
Guerre and pomme de terre are both feminine too, so you’d use la
- Comment on Um. I choose cow. 10 months ago:
Nipples?
- Comment on Smaug-72B-v0.1: The New Open-Source LLM Roaring to the Top of the Leaderboard 10 months ago:
All of them are gguf, yeah
- Comment on Smaug-72B-v0.1: The New Open-Source LLM Roaring to the Top of the Leaderboard 10 months ago:
I may need to lower it a bit more, yeah. Though when I try to to use offloading, I can see that vram usage doesn’t increase at all.
When I leave the setting at its default 100 value on the other hand, I see vram usage climb until it stops because there isn’t enough of it.
So I guess not all models support offloading?
- Comment on Smaug-72B-v0.1: The New Open-Source LLM Roaring to the Top of the Leaderboard 10 months ago:
I’m currently playing around with the Jan client, which uses the nitro engine. I think I need to read up on it more, because when I set the ngl value to 15 in order to offload 50% to GPU like the Jan guide says, nothing happens. Though that could be an issue specific to Jan.
- Comment on Smaug-72B-v0.1: The New Open-Source LLM Roaring to the Top of the Leaderboard 10 months ago:
That’s nice and all, but what are some FOSS models I can run on GPU with only 4GB?
I’ve tried Deepseek Coder, and it’s pretty nice for what I use it for. Then there’s TinyLlama, which… well it’s fast, but I need to be veeeery exact in how I prompt it.
- Comment on AMD’s new CPU hits 132fps in Fortnite without a graphics card 11 months ago:
I think I’m gonna get one of the higher end models, since it’ll be the best possible upgrade I can do on my motherboard.
So 5700X3D or 5800X3D, depending on what the prices look like whenever I’m gonna be in the marlet for them.
But it’s pretty cool that they made a 5600 variant too. Might as well use the chips they evidently still have left over
- Comment on AMD’s new CPU hits 132fps in Fortnite without a graphics card 11 months ago:
Oh, now that sounds like something I might like
I don’t have the fastest RAM out there, so whenever I upgrade from my 1600, I want an X3D variant to help with that