https://huggingface.co/google/gemma-4-31B/ (base models)
#2133
by SporkySporkness - opened
Hello, is it possible to quantize the base models for Gemma 4? A couple years ago when base models were routinely released, I used to play around with them for text completion. I would be interested to try with these new models.
Many thanks
https://huggingface.co/google/gemma-4-31B/
https://huggingface.co/google/gemma-4-26B-A4B-it
Edit: closed, I am attempting to make my own quants!
SporkySporkness changed discussion title from https://huggingface.co/google/gemma-4-31B/ (base model) to deleted
SporkySporkness changed discussion title from deleted to https://huggingface.co/google/gemma-4-31B/ (base models)
SporkySporkness changed discussion status to closed
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#gemma-4-31B-GGUF and https://hf.tst.eu/model#gemma-4-26B-A4B-it-GGUF for quants to appear.