mradermacher/Lumosia-MoE-4x10.7-GGUF
Quantization vs SteelStorage/Lumosia-MoE-4x10.7. mradermacher/Lumosia-MoE-4x10.7-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 194 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, Attention 0/192, other 0/48