lemmydividebyzero@reddthat.com to Technology@lemmy.worldEnglish · 3 个月前Opensource AI Must Winopensourceaimustwin.comexternal-linkmessage-square106fedilinkarrow-up1282arrow-down120
arrow-up1262arrow-down1external-linkOpensource AI Must Winopensourceaimustwin.comlemmydividebyzero@reddthat.com to Technology@lemmy.worldEnglish · 3 个月前message-square106fedilink
minus-squareZephyrXero@lemmy.worldlinkfedilinkEnglisharrow-up4arrow-down1·3 个月前I got Qwen 3.5:9b running on my 8GB GPU the other day, and it still has some room left over
minus-squareZephyrXero@lemmy.worldlinkfedilinkEnglisharrow-up4arrow-down1·3 个月前If the model dumps over to system ram it gets super slow, you ideally want it to fit completely in your VRAM
I got Qwen 3.5:9b running on my 8GB GPU the other day, and it still has some room left over
deleted by creator
If the model dumps over to system ram it gets super slow, you ideally want it to fit completely in your VRAM