mradermacher/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-i1-GGUF
Quantization vs DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B. mradermacher/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 135 tensors match exactly and 471 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/135, MLP 0/201, Attention 0/268