google/gemma-4-26B-A4B-it-qat-q4_0-gguf
Quantization vs google/gemma-4-26B-A4B-it-qat-q4_0-unquantized. google/gemma-4-26B-A4B-it-qat-q4_0-gguf is a GGUF quantization (Q4_0/Q6_K) of the same weights: 301 tensors match exactly and 206 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/271, MLP 0/90, other 0/30, Attention 0/115
2 derivatives checked
- NeoChen1024/gemma-4-26B-A4B-it-qat-W4A16: Quantization
- moebiusT7/gemma-4-26b-a4b-mobius-custom-c1: Identical copy