Some quick (non imatrix) quants I made for release.

I recommend using other quanters over me as they're better at it than I am.

Downloads last month
1,287
GGUF
Model size
31B params
Architecture
gemma4
Hardware compatibility
Log In to add your hardware

4-bit

6-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ConicCat/Gemma4-Garnet-31B-gguf

Quantized
(3)
this model