google/gemma-4-12B-it-qat-w4a16-ct
Quantization vs google/gemma-4-12B-it-qat-q4_0-unquantized. google/gemma-4-12B-it-qat-w4a16-ct is a quantized version of the other (I32/BF16).
3 derivatives checked
- g0chu/gemma-4-12B-it-qat-w4a16-ct-gguf: Quantization
- PreDoctor/gemma-4-12B-it-qat-w4a16-ct-PreTensor: Same weights, repacked
- speakrail/gemma-4-12B-it-qat-Speakrail: Adapter
8 other repos hold byte-for-byte identical weight files.