mradermacher/Abus-14B-Instruct-i1-GGUF
Quantization vs marcuscedricridia/Abus-14B-Instruct. mradermacher/Abus-14B-Instruct-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 241 tensors match exactly and 338 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/336