mradermacher/Apertus-70B-Instruct-2509-abliterated-i1-GGUF
Quantization vs nicoboss/Apertus-70B-Instruct-2509-abliterated. mradermacher/Apertus-70B-Instruct-2509-abliterated-i1-GGUF is a GGUF quantization (Q5_K_S) of the same weights: 321 tensors match exactly and 482 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/321, MLP 0/160, Attention 0/320, lm_head 0/1