mradermacher/DeepSeek-GRM-27B-GGUF
Quantization vs BBQGOD/DeepSeek-GRM-27B. mradermacher/DeepSeek-GRM-27B-GGUF is a GGUF quantization (Q8_0) of the same weights: 185 tensors match exactly and 323 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/185, Attention 0/184, MLP 0/138