mradermacher/SakaMoe-3x14B-Instruct-GGUF
Quantization vs Sakalti/SakaMoe-3x14B-Instruct. mradermacher/SakaMoe-3x14B-Instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 338 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/192, Attention 0/336, lm_head 0/1