dev7a/Laguna-S-2.1-DFlash-GGUF
Quantization vs poolside/Laguna-S-2.1-DFlash. dev7a/Laguna-S-2.1-DFlash-GGUF is a GGUF quantization (Q8_0) of the same weights: 25 tensors match exactly and 25 within quantization error.
Tensors changed: other 0/1, Norms 0/25, MLP 0/18, Attention 0/6