model family

Qwen-Image

Published by Qwen. No machine on this network has measured this family yet. The members below are what the catalog knows exists; nothing about what they can do is claimed here until somebody runs one.

what it takes, what it returns
text → image

Declared by the network’s catalog, not measured — a signature says what this family would be asked. Whether it answered is the signed capability flags on each member.

0 of 4 builds measured · 4 still open
Qwen-Image 20B1 known build · not measured
2512-lightning1 known build · not measured
lightning1 known build · not measured
nunchaku-edit1 known build · not measured

Builds this network knows of

Declared, not measured — this is what the catalog says exists and what it would cost a machine to hold. Nothing here is signed, and none of it claims the build works.

how much memory does your machine have

0 of 4 builds fit a 16 GB machine — budgeting 70% of it, or 11.2 GiB, because the cache and the runtime want the rest.

  • lightx2v/Qwen-Image-LightningBF16diffusersderived by lightx2v
    16.6 GiB
  • Qwen/Qwen-ImageBF16diffuserspublished by Qwen
    41.0 GiB
  • lightx2v/Qwen-Image-2512-LightningBF16diffusersderived by lightx2v
    96.9 GiB
  • nunchaku-ai/nunchaku-qwen-image-editdiffusersderived by nunchaku-ai
    137.5 GiB

Sizes are what the catalog declares, not what a machine measured — fitting on disk is necessary and not sufficient. Nobody here has run these on your machine, and this narrows the candidates rather than certifying one.

the same builds, by member
Qwen-Image 20B20B
Qwen/Qwen-ImageBF16diffusers41.0 GiB on diskpublished by Qwen
2512-lightning
lightx2v/Qwen-Image-2512-LightningBF16diffusers96.9 GiB on diskderived by lightx2v
lightning
lightx2v/Qwen-Image-LightningBF16diffusers16.6 GiB on diskderived by lightx2v
nunchaku-edit
nunchaku-ai/nunchaku-qwen-image-editdiffusers137.5 GiB on diskderived by nunchaku-ai
ask your own gram

Your concierge can answer this from the network rather than from this page. The ask carries the operator id, so it resolves to a capability and an engine — not to a name somebody has to recognise.

What has this network measured about the Qwen-Image family (epn.family.qwen-image), and can my gram run any of it? See /inferences/qwen-image

open a gramx with this ask →epn.family.qwen-image