mradermacher/A2R-30B-A3B-GGUF
Quantization vs PleasedPenguin/A2R-30B-A3B. mradermacher/A2R-30B-A3B-GGUF is a GGUF quantization (Q8_0) of the same weights: 193 tensors match exactly and 194 within quantization error.
Tensors changed: Norms 0/193, Attention 0/192, Embeddings 0/1, lm_head 0/1