mradermacher/Cipher-20B-i1-GGUF
Quantization vs HelpingAI/Cipher-20B. mradermacher/Cipher-20B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 346 tensors match exactly and 485 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/139, MLP 0/207, Attention 0/483, lm_head 0/1