mradermacher/Barcenas-StyleTune-31B-Fable-GGUF
Quantization vs Iloqt/Barcenas-StyleTune-31B-Fable. mradermacher/Barcenas-StyleTune-31B-Fable-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 412 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230