mmnga-o/NVIDIA-Nemotron-Nano-9B-v2-Japanese-gguf
Quantization vs nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese. mmnga-o/NVIDIA-Nemotron-Nano-9B-v2-Japanese-gguf is a GGUF quantization (Q8_0) of the same weights: 57 tensors match exactly and 2 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, lm_head 0/1