This is a 7.05bpw quant that follows bartowski's Gemma 4 31b Q6_K_L quantization scheme. Among other things, it uses Q8_0 for embed and output weights.
The following imatrix was used to create this quant, provided by the model's creator, zerofata.
mmproj and mtp meant for default Gemma 4 31b instruct work properly with this model and were also uploaded to this repository. They were made by bartowski and taken from his gemma-4-31B-it-GGUF repository.
