Bazwilks/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF
Quantization vs DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking. Bazwilks/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF is a GGUF quantization (Q8_0) of the same weights: 266 tensors match exactly and 361 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/241, MLP 0/288, Attention 0/96