mradermacher

/

model_requests

like 180

it's done!
https://hf.tst.eu/model#gemma-4-31B-Queen-it-qat-q4_0-unquantized-GGUF

Hi mradermacher, RichardErkhov
Thank you so much for your continuous support in quantizing my models.
I noticed that the mmproj file for my model aifeifei798/gemma-4-31B-Queen-it-qat-q4_0-unquantized (and likely the 12B version as well) was not generated during the GGUF conversion process.
Could you please look into this when you have a moment? I tested generating the mmproj file locally, and it completed without any issues (for example, I was able to successfully generate mmproj-gemma-4-12B-Queen-it-qat-unquantized-BF16.gguf and mmproj-gemma-4-31B-Queen-it-qat-unquantized-BF16.gguf).
If possible, could you please regenerate and upload the corresponding mmproj files?
Thank you again for your time and help!

https://huggingface.co/mradermacher/gemma-4-31B-Queen-it-qat-q4_0-unquantized-i1-GGUF/blob/main/gemma-4-31B-Queen-it-qat-q4_0-unquantized.imatrix.gguf

it is there

thanks,Good job,XD