mradermacher

/

model_requests

Like 208

It's queued!

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#Boulesis-26B-A4B-GGUF for quants to appear.

@redaihf Thank you very much!

Did something go wrong with this model?

Requested it again. Hoping nothing breaks.

Probably something really did break. @mradermacher can you check? Thanks!

Yes, llamacpp update broke, but I didnt find time to requeue. I will do it soon =)

Thank you for your work! We'll wait as long as it takes.

requeued, but it needs to be processed on nico1, but it's night and the server is sleeping, check on it in the morning

nico1 is up on the status board but this model is not.

@RichardErkhov Sorry to nudge, but it seems the model dropped out of the queue.

On the advice of @Vortex5 added to repo processor_config.jsonand copy the original of chat_template.jinja from https://huggingface.co/google/gemma-4-26B-A4B-it

@RichardErkhov Hello! Could I ask you to try adding the model to the processing queue again? I fixed a couple of things that might have broken the quantization.

It's queued!

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#Boulesis-26B-A4B-GGUF for quants to appear.

@RichardErkhov Thank you very much!!! God bless you

@redaihf Will you close this discussion?