dahara1/shisa-v2.1-llama3.2-3b-UD-japanese-imatrix
Quantization vs shisa-ai/shisa-v2.1-llama3.2-3b. dahara1/shisa-v2.1-llama3.2-3b-UD-japanese-imatrix is a GGUF quantization (Q8_0) of the same weights: 57 tensors match exactly and 197 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112