mradermacher/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored-GGUF
Quantization (fewer layers) vs DavidAU/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored. mradermacher/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored-GGUF matches part of DavidAU/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored (627 of its 1066 tensors; the rest of DavidAU/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored has no counterpart). On the shared part: mradermacher/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 338 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192, lm_head 0/1