Melvin56/kanana-nano-2.1b-instruct-GGUF
Quantization vs kakaocorp/kanana-nano-2.1b-instruct. Melvin56/kanana-nano-2.1b-instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 65 tensors match exactly and 225 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128