mradermacher/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT-i1-GGUF
Quantization (fewer layers) vs DavidAU/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT. mradermacher/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT-i1-GGUF matches part of DavidAU/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT (808 of its 1247 tensors; the rest of DavidAU/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT has no counterpart). On the shared part: mradermacher/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT-i1-GGUF is a GGUF quantization (Q6_K) 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