mradermacher/magibu-11b-v8-GGUF
Quantization (fewer layers) vs alibayram/magibu-11b-v8. mradermacher/magibu-11b-v8-GGUF matches part of alibayram/magibu-11b-v8 (626 of its 1065 tensors; the rest of alibayram/magibu-11b-v8 has no counterpart). On the shared part: mradermacher/magibu-11b-v8-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192