Abiray/Krea-2-Turbo-GGUF
Quantization vs krea/Krea-2-Turbo. Abiray/Krea-2-Turbo-GGUF is a GGUF quantization (Q8_0) of the same weights: 167 tensors match exactly and 263 within quantization error.
Tensors changed: Norms 0/129, other 0/36, MLP 0/105, Attention 0/160