mradermacher/mythos-9b-merged-GGUF
Quantization vs King3Djbl/mythos-9b-merged. mradermacher/mythos-9b-merged-GGUF is a GGUF quantization (F16) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: lm_head 0/1, Norms 0/145, other 0/1, Attention 0/144, MLP 0/108