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