mradermacher/Chaifighter-20B-GGUF
Quantization vs matchaaaaa/Chaifighter-20B. mradermacher/Chaifighter-20B-GGUF is a GGUF quantization (Q8_0) of the same weights: 189 tensors match exactly and 660 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/189, MLP 0/282, Attention 0/376