Nimbz/Schattenblume-31B-GGUF
Quantization (fewer layers) vs Nimbz/Schattenblume-31B. Nimbz/Schattenblume-31B-GGUF matches part of Nimbz/Schattenblume-31B (772 of its 1188 tensors; the rest of Nimbz/Schattenblume-31B has no counterpart). On the shared part: Nimbz/Schattenblume-31B-GGUF is a GGUF quantization (Q8_0/BF16) of the same weights: 592 tensors match exactly and 180 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230