mradermacher/VirtuosoSmall-InstructModelStock-GGUF
Quantization vs mergekit-community/VirtuosoSmall-InstructModelStock. mradermacher/VirtuosoSmall-InstructModelStock-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 338 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/336