steampunque/translategemma-12b-it-MP-GGUF
Quantization (fewer layers) vs google/translategemma-12b-it. steampunque/translategemma-12b-it-MP-GGUF matches part of google/translategemma-12b-it (626 of its 1065 tensors; the rest of google/translategemma-12b-it has no counterpart). On the shared part: steampunque/translategemma-12b-it-MP-GGUF is a GGUF quantization (Q4_E_H) 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