mradermacher/Gemma-3-Glitter-12B-i1-GGUF
Quantization (fewer layers) vs allura-org/Gemma-3-Glitter-12B. mradermacher/Gemma-3-Glitter-12B-i1-GGUF matches part of allura-org/Gemma-3-Glitter-12B (625 of its 1065 tensors; the rest of allura-org/Gemma-3-Glitter-12B has no counterpart). On the shared part: mradermacher/Gemma-3-Glitter-12B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 289 tensors match exactly and 336 within quantization error.
Tensors changed: Norms 0/289, MLP 0/144, Attention 0/192