mradermacher/gemma3-12b-tolkien_v2-GGUF
Quantization (fewer layers) vs berkaygkv54/gemma3-12b-tolkien_v2. mradermacher/gemma3-12b-tolkien_v2-GGUF matches part of berkaygkv54/gemma3-12b-tolkien_v2 (626 of its 1065 tensors; the rest of berkaygkv54/gemma3-12b-tolkien_v2 has no counterpart). On the shared part: mradermacher/gemma3-12b-tolkien_v2-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