mradermacher/Iambe-20b-DARE-v2-GGUF
Quantization vs athirdpath/Iambe-20b-DARE-v2. mradermacher/Iambe-20b-DARE-v2-GGUF is a GGUF quantization (Q8_0) of the same weights: 126 tensors match exactly and 435 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/125, MLP 0/186, Attention 0/248, lm_head 0/1