Baekpica/Naive-N0.5-Flash-Mixed-Quant-GGUF
Quantization vs NaiveAI/Naive-N0.5-Flash. Baekpica/Naive-N0.5-Flash-Mixed-Quant-GGUF is a GGUF quantization (IQ2_XXS/IQ2_XS) of the same weights: 171 tensors match exactly and 197 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/115, MLP 0/50, Attention 0/201, lm_head 0/1
1 derivatives checked
- AMAImedia/Naive-N0.5-Flash-Mixed-Quant-GGUF: Identical copy