yileneko/qwen2.5-neko
Quantization vs Qwen/Qwen2.5-0.5B-Instruct. yileneko/qwen2.5-neko is a GGUF quantization (Q5_0/Q8_0) of the same weights: 121 tensors match exactly and 169 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168