mitkox/Huihui-Qwen3.8-27B-abliterated-Q4_K_M-GGUF
Quantization vs huihui-ai/Huihui-Qwen3.8-27B-abliterated. mitkox/Huihui-Qwen3.8-27B-abliterated-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 161 tensors match exactly and 258 within quantization error.
Tensors changed: Norms 0/161, MLP 0/192, Attention 0/64, Embeddings 0/1, lm_head 0/1