INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0-GGUF
Quantization (fewer layers) vs INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0. INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0-GGUF matches part of INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0 (626 of its 1065 tensors; the rest of INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0 has no counterpart). On the shared part: INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0-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