mradermacher/BigCodeLlama-92b-i1-GGUF
Quantization vs nisten/BigCodeLlama-92b. mradermacher/BigCodeLlama-92b-i1-GGUF is a GGUF quantization (IQ4_XS) of the same weights: 215 tensors match exactly and 751 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/215, MLP 0/321, Attention 0/428, lm_head 0/1