https://huggingface.co/nightmedia/Qwen3-30B-A3B-Architect7

#1628
by nightmedia - opened

Dear Team Radermacher,
please create quants of this model:
https://huggingface.co/nightmedia/Qwen3-30B-A3B-Architect7

Architect7 Metrics (qx86-hi variant shown)

0.563,0.737,0.878,0.758,0.448,0.803,0.698

It's gated. I qill quant it as soon you accept my access request.

Thank you, added

Could we try again? :)

I already queued it yesterday but it apparently had to wait in the queue due to nico1 being busy with other models.

1 additional job(s) in wait queue (total estimated size 0.061TB, imatrix 0.061TB, lownice 1):
-2000   62 si Qwen3-30B-A3B-Architect7                     (worker nico1)

I now force pushed it to nico1 immediately and it is currently getting processed without any issues:

-2000   61 Qwen3-30B-A3B-Architect7                      run/imatrix (GPU-18) 16/48 3.72s/c 9.3/19.7m(15.1-16.1) [183/318] 11.0480
-2000   62 si Qwen3-30B-A3B-Architect7                     run/static 5/12,Q6_K [159/579] (hfu Q8_0)

Thank you πŸ™ β€οΈπŸ˜€

Sign up or log in to comment