mradermacher/BigAurelian-v0.5-120b-32k-GGUF
Quantization vs llmixer/BigAurelian-v0.5-120b-32k. mradermacher/BigAurelian-v0.5-120b-32k-GGUF is a GGUF quantization (IQ3_XS) of the same weights: 276 tensors match exactly and 960 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/275, MLP 0/411, Attention 0/548, lm_head 0/1