DZgas/

gemma-4-31B-it-Q4_K-local-Q6_K-global-GGUF

I've noticed that higher quality for global layers (17% of the model) gives better overall quality than the standard mixed like compression, for models of the same size or 1-2 gigabytes larger.

Better than new QAT from google (or unsloth/gemma-4-31B-it-qat) ⸺ The QAT model makes gross factual errors when writing names or exact facts, which neither the original model nor my model does. Probably, q4_0 is much more important for global layers than I thought, and it's broken in QAT models. Perhaps if you replace all the global layers and embeddings with q6_k in the QAT model, it will be better. I'm even curious if the QAT q4_0 local layer will be better in quality than the q4_k layers from the original model. But I won't do such complex merges, too lazy.

q.bat