InferenceIllusionist/dolphin-2.9.1-mixtral-1x22b-iMat-GGUF
Quantization vs dphn/dolphin-2.9.1-mixtral-1x22b. InferenceIllusionist/dolphin-2.9.1-mixtral-1x22b-iMat-GGUF is a GGUF quantization (Q8_0) of the same weights: 113 tensors match exactly and 226 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/113, Attention 0/224, lm_head 0/1