mradermacher/Mixolar-4x7b-GGUF
Quantization vs shadowml/Mixolar-4x7b. mradermacher/Mixolar-4x7b-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 194 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, Attention 0/192, other 0/48