Markobes/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored-Q8_0-GGUF
Quantization (fewer layers) vs DavidAU/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored. Markobes/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored-Q8_0-GGUF matches part of DavidAU/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored (626 of its 1065 tensors; the rest of DavidAU/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored has no counterpart). On the shared part: Markobes/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored-Q8_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