redashes/Qwen3.8-27B-SSMFIX-apostate-GSQ-RCO-IQ3_S
Quantization vs redashes/Qwen3.8-27B-BF16-SSMFIX-apostate. redashes/Qwen3.8-27B-SSMFIX-apostate-GSQ-RCO-IQ3_S is a GGUF quantization (IQ3_S/IQ4_XS) 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