mradermacher/Hy-MT2-30B-A3B-uncensored-heretic-GGUF
Quantization vs OS-Software/Hy-MT2-30B-A3B-uncensored-heretic. mradermacher/Hy-MT2-30B-A3B-uncensored-heretic-GGUF is a GGUF quantization (Q8_0) of the same weights: 246 tensors match exactly and 338 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/193, MLP 0/197, Attention 0/192