ysn-rfd/gemma-3-it-vl-40B-Gemini-Heretic-Uncensored-Thinking-Q8_0-GGUF
Quantization vs DavidAU/gemma-3-it-vl-40B-Gemini-Heretic-Uncensored-Thinking. ysn-rfd/gemma-3-it-vl-40B-Gemini-Heretic-Uncensored-Thinking-Q8_0-GGUF is a GGUF quantization (Q8_0) of the same weights: 565 tensors match exactly and 659 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/565, MLP 0/282, Attention 0/376