☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 7 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-square7fedilinkarrow-up137cross-posted to: Aii@programming.dev
arrow-up137imageGPT-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 · 7 hours agomessage-square7fedilinkcross-posted to: Aii@programming.dev
minus-squareCameronDev@programming.devlinkfedilinkarrow-up7·5 hours agoThis is for qwen 3.5, not 3.6, but the vram requirements are a little out there for most: https://willitrunai.com/blog/qwen-3-5-27b-vram-requirements 16 to 55GB…
minus-squareBlisterexe@lemmy.ziplinkfedilinkarrow-up2·5 hours agoI mean that’s high but not unreasonable, especially with unified ram machines
minus-square☆ Yσɠƚԋσʂ ☆@lemmy.mlOPlinkfedilinkarrow-up2·5 hours agoand it’s even lower with MTP https://huggingface.co/unsloth/Qwen3.6-27B-MTP-GGUF
[citation needed]
This is for qwen 3.5, not 3.6, but the vram requirements are a little out there for most:
https://willitrunai.com/blog/qwen-3-5-27b-vram-requirements
16 to 55GB…
I mean that’s high but not unreasonable, especially with unified ram machines
and it’s even lower with MTP https://huggingface.co/unsloth/Qwen3.6-27B-MTP-GGUF