mradermacher/miquliz-120b-v2.0-GGUF
Quantization vs wolfram/miquliz-120b-v2.0. mradermacher/miquliz-120b-v2.0-GGUF is a GGUF quantization (IQ3_XS) of the same weights: 281 tensors match exactly and 982 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/281, MLP 0/420, Attention 0/560, lm_head 0/1