mmnga/llm-jp-3.1-1.8b-instruct4-gguf
Quantization vs llm-jp/llm-jp-3.1-1.8b-instruct4. mmnga/llm-jp-3.1-1.8b-instruct4-gguf is a GGUF quantization (Q8_0) of the same weights: 49 tensors match exactly and 170 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96