mradermacher/Rubicon-Preview-GGUF
Quantization vs inclusionAI/Rubicon-Preview. mradermacher/Rubicon-Preview-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 194 within quantization error.
Tensors changed: Norms 0/193, Attention 0/192, MLP 0/48, Embeddings 0/1, lm_head 0/1