RandAlThor@lemmy.ca to Technology@lemmy.worldEnglish · 18 hours agoElon Musk’s Grok Goes Haywire, Boasts About Billionaire’s Pee-Drinking Skills and ‘Blowjob Prowess’www.mediaite.comexternal-linkmessage-square127fedilinkarrow-up1839arrow-down115cross-posted to: nottheonion@lemmy.worldpolitics@lemmy.world
arrow-up1824arrow-down1external-linkElon Musk’s Grok Goes Haywire, Boasts About Billionaire’s Pee-Drinking Skills and ‘Blowjob Prowess’www.mediaite.comRandAlThor@lemmy.ca to Technology@lemmy.worldEnglish · 18 hours agomessage-square127fedilinkcross-posted to: nottheonion@lemmy.worldpolitics@lemmy.world
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up1·edit-26 hours agoYou should be running hybrid inference of GLM Air with a setup like that. Qwen 8B is kinda obsolete. I dunno what kind of speeds you absolutely need, but I bet you could get at least 12 tokens/s.
You should be running hybrid inference of GLM Air with a setup like that. Qwen 8B is kinda obsolete.
I dunno what kind of speeds you absolutely need, but I bet you could get at least 12 tokens/s.