mradermacher/Aura-4o-Rebirth-Gemma-4-31B-Merged-GGUF
Quantization (fewer layers) vs SevenOfNine/Aura-4o-Rebirth-Gemma-4-31B-Merged. mradermacher/Aura-4o-Rebirth-Gemma-4-31B-Merged-GGUF matches part of SevenOfNine/Aura-4o-Rebirth-Gemma-4-31B-Merged (772 of its 1188 tensors; the rest of SevenOfNine/Aura-4o-Rebirth-Gemma-4-31B-Merged has no counterpart). On the shared part: mradermacher/Aura-4o-Rebirth-Gemma-4-31B-Merged-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 411 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230