TheBloke/Mixtral_11Bx2_MoE_19B-GGUF
Quantization vs cloudyu/Mixtral_11Bx2_MoE_19B. TheBloke/Mixtral_11Bx2_MoE_19B-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 194 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, other 0/48, Attention 0/192