google/gemma-4-E4B-it-qat-w4a16-ct

Quantization vs google/gemma-4-E4B-it-qat-q4_0-unquantized. google/gemma-4-E4B-it-qat-w4a16-ct is a quantized version of the other (BF16/I32).

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse