mradermacher/ERank-32B-GGUF
Quantization vs Alibaba-NLP/ERank-32B. mradermacher/ERank-32B-GGUF is a GGUF quantization (Q8_0) of the same weights: 257 tensors match exactly and 450 within quantization error.
Tensors changed: Attention 0/256, Norms 0/257, MLP 0/192, lm_head 0/1, Embeddings 0/1