liodon-ai/MaralGPT-Mythos-9B-2606-GGUF-imatrix-GGUF
Quantization vs MaralGPT/MaralGPT-Mythos-9B-2606-GGUF. liodon-ai/MaralGPT-Mythos-9B-2606-GGUF-imatrix-GGUF is a GGUF quantization (Q8_0) of the same weights: 177 tensors match exactly and 250 within quantization error.
Tensors changed: lm_head 0/1, other 0/145, Norms 0/105, Attention 0/80, MLP 0/96