mradermacher/kanana-2-3b-instruct-i1-GGUF
Quantization vs kakaocorp/kanana-2-3b-instruct. mradermacher/kanana-2-3b-instruct-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 129 tensors match exactly and 226 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/96, Attention 0/128