lemmydividebyzero@reddthat.com to Technology@lemmy.worldEnglish · 2 days agoOpensource AI Must Winopensourceaimustwin.comexternal-linkmessage-square98fedilinkarrow-up1280arrow-down120cross-posted to: technology@lemmy.mltechnology@hexbear.net
arrow-up1260arrow-down1external-linkOpensource AI Must Winopensourceaimustwin.comlemmydividebyzero@reddthat.com to Technology@lemmy.worldEnglish · 2 days agomessage-square98fedilinkcross-posted to: technology@lemmy.mltechnology@hexbear.net
minus-squareshortwavesurfer@lemmy.ziplinkfedilinkEnglisharrow-up5·2 days agoNot the big ones, no. But I think almost everybody can run one with seven billion parameters.
minus-squaremabeledo@lemmy.worldlinkfedilinkEnglisharrow-up1arrow-down1·2 days agoConsidering that the vast majority of PCs in the world have 8GB of RAM at most, I still doubt it.
minus-squareshortwavesurfer@lemmy.ziplinkfedilinkEnglisharrow-up4·2 days agoI ran it on my 8GB RAM desktop.
minus-squaremabeledo@lemmy.worldlinkfedilinkEnglisharrow-up1·2 days agoI mean if that’s all that would be loaded in memory, sure.
minus-squareZephyrXero@lemmy.worldlinkfedilinkEnglisharrow-up4·2 days 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 days agoI was talking about combined system RAM. People often overestimate what the average system specs are.
minus-squareZephyrXero@lemmy.worldlinkfedilinkEnglisharrow-up4·2 days agoIf the model dumps over to system ram it gets super slow, you ideally want it to fit completely in your VRAM
Not the big ones, no. But I think almost everybody can run one with seven billion parameters.
Considering that the vast majority of PCs in the world have 8GB of RAM at most, I still doubt it.
I ran it on my 8GB RAM desktop.
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