Grunzig/gemma-4-12B-it-qat-oQ4e-fp16-mtp

Quantization vs google/gemma-4-12B-it-qat-q4_0-unquantized. Grunzig/gemma-4-12B-it-qat-oQ4e-fp16-mtp is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse