k0ndra/Qwen3.5-35B-A3B-heretic-v2-ja-imatrix-GGUF
Quantization vs llmfan46/Qwen3.5-35B-A3B-ultra-uncensored-heretic. k0ndra/Qwen3.5-35B-A3B-heretic-v2-ja-imatrix-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 141 tensors match exactly and 162 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/101, MLP 0/160, Attention 0/40