ReadyArt/Omega-Evolution-9B-v2.0-GGUF
Quantization vs ReadyArt/Omega-Evolution-9B-v2.0. ReadyArt/Omega-Evolution-9B-v2.0-GGUF is a GGUF quantization (Q8_0_ATTN8_SSM8_HB16) of the same weights: 83 tensors match exactly and 128 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32