InferForge/Ornith-1.5-9B-Q4_K_M
Quantization vs ornith-ai/Ornith-1.5-9B-GGUF. InferForge/Ornith-1.5-9B-Q4_K_M is a GGUF quantization (Q4_K_M) of the same weights: 184 tensors match exactly and 258 within quantization error.
Tensors changed: other 0/146, Norms 0/112, Attention 0/84, MLP 0/99, lm_head 0/1