mradermacher/BigOrca-2-XB-GGUF
Quantization vs Joseph717171/BigOrca-2-XB. mradermacher/BigOrca-2-XB-GGUF is a GGUF quantization (Q8_0) of the same weights: 142 tensors match exactly and 491 within quantization error.
Tensors changed: Norms 0/141, MLP 0/210, Attention 0/280, Embeddings 0/1, lm_head 0/1