☆ Yσɠƚԋσʂ ☆@lemmygrad.ml to technology@hexbear.netEnglish · 3 days agoGPT-5, the world best model just 1 year ago, is today inferior to Qwen3.6 27B that you can run on your desktoplemmygrad.mlimagemessage-square29fedilinkarrow-up176arrow-down10
arrow-up176arrow-down1imageGPT-5, the world best model just 1 year ago, is today inferior to Qwen3.6 27B that you can run on your desktoplemmygrad.ml☆ Yσɠƚԋσʂ ☆@lemmygrad.ml to technology@hexbear.netEnglish · 3 days agomessage-square29fedilink
minus-squareBountifulEggnog [it/its, she/her]@hexbear.netlinkfedilinkEnglisharrow-up5·edit-23 days agoRunning fp16, in current year? https://huggingface.co/unsloth/Qwen3.6-27B-GGUF even 5ks is 19gb. Plus context but that still fully fits on a 3090. But even splitting it across gpu + cpu isn’t as bad as it could be.
Running fp16, in current year?
https://huggingface.co/unsloth/Qwen3.6-27B-GGUF
even 5ks is 19gb. Plus context but that still fully fits on a 3090. But even splitting it across gpu + cpu isn’t as bad as it could be.