Cannae-AI/ReasoningLlama-Math-1B-IT-gguf
Quantization vs Cannae-AI/ReasoningLlama-Math-1B-IT. Cannae-AI/ReasoningLlama-Math-1B-IT-gguf is a GGUF quantization (Q8_0) of the same weights: 33 tensors match exactly and 113 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64