beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj
Quantization (fewer layers) vs INSAIT-Institute/BgGPT-Gemma-3-27B-IT. beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj matches part of INSAIT-Institute/BgGPT-Gemma-3-27B-IT (808 of its 1247 tensors; the rest of INSAIT-Institute/BgGPT-Gemma-3-27B-IT has no counterpart). On the shared part: beleata74/BgGPT-Gemma-3-27B-IT-V2-GGUF-mmproj is a GGUF quantization (Q8_0) of the same weights: 373 tensors match exactly and 435 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/186, Attention 0/248