ysn-rfd/Arch-Function-Chat-3B-GGUF
Quantization vs katanemo/Arch-Function-Chat-3B. ysn-rfd/Arch-Function-Chat-3B-GGUF is a GGUF quantization (Q8_0) of the same weights: 181 tensors match exactly and 253 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252