cdanis/Ornith-1.5-397B-GGUF-imatrix
Quantization vs ornith-ai/Ornith-1.5-397B. cdanis/Ornith-1.5-397B-GGUF-imatrix is a GGUF quantization (IQ4_XS/Q8_0) of the same weights: 211 tensors match exactly and 242 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/151, MLP 0/240, Attention 0/60, lm_head 0/1