mradermacher/gemma-3-12b-pt-conductivity-GGUF
Quantization (fewer layers) vs Taekgi/gemma-3-12b-pt-conductivity. mradermacher/gemma-3-12b-pt-conductivity-GGUF matches part of Taekgi/gemma-3-12b-pt-conductivity (626 of its 1065 tensors; the rest of Taekgi/gemma-3-12b-pt-conductivity has no counterpart). On the shared part: mradermacher/gemma-3-12b-pt-conductivity-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