nisten/mixtral8x22-imatrix-gguf
Quantization vs mistral-community/Mixtral-8x22B-v0.1. nisten/mixtral8x22-imatrix-gguf is a GGUF quantization (IQ2_S/IQ4_NL) of the same weights: 169 tensors match exactly and 226 within quantization error.
Tensors changed: Embeddings 0/1, other 0/56, Attention 0/224, Norms 0/113, lm_head 0/1