leon-se/gemma-3-27b-it-qat-W4A16-G128

Quantization vs google/gemma-3-27b-it-qat-q4_0-unquantized. leon-se/gemma-3-27b-it-qat-W4A16-G128 is a quantized version of the other (I32/BF16).

On the Hub · Downloads on Model Pulse