mradermacher/kanana-1.5-15.7b-a3b-instruct-GGUF
Quantization vs kakaocorp/kanana-1.5-15.7b-a3b-instruct. mradermacher/kanana-1.5-15.7b-a3b-instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 97 tensors match exactly and 130 within quantization error.
Tensors changed: other 0/32, Norms 0/65, Attention 0/128, Embeddings 0/1, lm_head 0/1