The Picard Maneuver@lemmy.worldM to memes@lemmy.world · 2 months agoThey're all vitallemmy.worldimagemessage-square136fedilinkarrow-up11.24Karrow-down126
arrow-up11.22Karrow-down1imageThey're all vitallemmy.worldThe Picard Maneuver@lemmy.worldM to memes@lemmy.world · 2 months agomessage-square136fedilink
minus-squareStephen G. Tallentyre@lemmy.worldlinkfedilinkarrow-up2·2 months agoThe machine I had before this had 4 GB, lol. That’s why I put so much of the budget into RAM when I built this one.
minus-squareHonytawk@lemmy.ziplinkfedilinkarrow-up6·2 months agoI mean, you can never have too much ram. But if you don’t use it in its entirety, it is kind of useless.
minus-squareAnUnusualRelic@lemmy.worldlinkfedilinkarrow-up1·2 months agoThat’s the system’s job. It can cache stuff or whatever.
minus-squarePossibly linux@lemmy.ziplinkfedilinkEnglisharrow-up1·edit-22 months ago192GB is way to big to be used as a cache However, you probably could run some of the huge language models
minus-squareAnUnusualRelic@lemmy.worldlinkfedilinkarrow-up2·2 months agoYou’re underestimating the cache.
minus-squarePossibly linux@lemmy.ziplinkfedilinkEnglisharrow-up1·2 months agoYou are underestimating writebacks. You won’t use that much on a normal filesystem and with ZFS you will only use that with bigger amounts of data
The machine I had before this had 4 GB, lol. That’s why I put so much of the budget into RAM when I built this one.
I mean, you can never have too much ram.
But if you don’t use it in its entirety, it is kind of useless.
That’s the system’s job. It can cache stuff or whatever.
192GB is way to big to be used as a cache
However, you probably could run some of the huge language models
You’re underestimating the cache.
You are underestimating writebacks. You won’t use that much on a normal filesystem and with ZFS you will only use that with bigger amounts of data