molbal/krea2-gguf
Quantization vs krea/Krea-2-Raw. molbal/krea2-gguf is a GGUF quantization (Q4_0) of the same weights: 172 tensors match exactly and 258 within quantization error.
Tensors changed: Norms 0/129, other 0/36, MLP 0/105, Attention 0/160
Quantization vs krea/Krea-2-Raw. molbal/krea2-gguf is a GGUF quantization (Q4_0) of the same weights: 172 tensors match exactly and 258 within quantization error.
Tensors changed: Norms 0/129, other 0/36, MLP 0/105, Attention 0/160