☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 13 hours agoGPT-5, the world best model just 1 year ago, is today inferior to Qwen3.6 27B that you can run on your desktoplemmy.mlimagemessage-square29fedilinkarrow-up172arrow-down111
arrow-up161arrow-down1imageGPT-5, the world best model just 1 year ago, is today inferior to Qwen3.6 27B that you can run on your desktoplemmy.ml☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 13 hours agomessage-square29fedilink
minus-squareCameronDev@programming.devlinkfedilinkarrow-up1·edit-22 hours agoFull quantisation? I’ve only got a 8GB 3070, but I’ll give it a go Edit: Tried the unsloth/qwen3.6 with llama.CPP, and it failed to allocate a 26GB Vulcan buffer and died. Dunno what magic your using, no luck for me though :(
Full quantisation? I’ve only got a 8GB 3070, but I’ll give it a go
Edit: Tried the unsloth/qwen3.6 with llama.CPP, and it failed to allocate a 26GB Vulcan buffer and died. Dunno what magic your using, no luck for me though :(