BroLaurens/gemma-4-31B-it-qat-NVFP4-GGUF

Not comparable yet vs melcheikh/gemma-4-31B-it-qat-NVFP4-mse-Blackwell. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (362 of 2418/1653 match), usually an architecture llama.cpp's name map doesn't cover yet.

On the Hub · Downloads on Model Pulse