mradermacher/kanana-1.5-8b-instruct-2505-i1-GGUF
Quantization vs OpenLLM-Korea/kanana-1.5-8b-instruct-2505. mradermacher/kanana-1.5-8b-instruct-2505-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 65 tensors match exactly and 226 within quantization error.
Tensors changed: MLP 0/96, Norms 0/65, Attention 0/128, Embeddings 0/1, lm_head 0/1