lemmydividebyzero@reddthat.com to Technology@lemmy.worldEnglish · 2 months agoOpensource AI Must Winopensourceaimustwin.comexternal-linkmessage-square111fedilinkarrow-up1284arrow-down120
arrow-up1264arrow-down1external-linkOpensource AI Must Winopensourceaimustwin.comlemmydividebyzero@reddthat.com to Technology@lemmy.worldEnglish · 2 months agomessage-square111fedilink
minus-squaremabeledo@lemmy.worldlinkfedilinkEnglisharrow-up1·2 months agoI mean if that’s all that would be loaded in memory, sure.
minus-squareZephyrXero@lemmy.worldlinkfedilinkEnglisharrow-up4arrow-down1·2 months agoI got Qwen 3.5:9b running on my 8GB GPU the other day, and it still has some room left over
minus-squaremabeledo@lemmy.worldlinkfedilinkEnglisharrow-up2·2 months agoI was talking about combined system RAM. People often overestimate what the average system specs are.
minus-squareZephyrXero@lemmy.worldlinkfedilinkEnglisharrow-up4arrow-down1·2 months agoIf the model dumps over to system ram it gets super slow, you ideally want it to fit completely in your VRAM
I mean if that’s all that would be loaded in memory, sure.
I got Qwen 3.5:9b running on my 8GB GPU the other day, and it still has some room left over
I was talking about combined system RAM. People often overestimate what the average system specs are.
If the model dumps over to system ram it gets super slow, you ideally want it to fit completely in your VRAM