coder3101 / gemma-4-12B-it-qat-q4_0-unquantized-heretic

[!Note] This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. Four versions of the QAT checkpoi…