mradermacher/Llama-3.2-3B-MoE-4Expert-i1-GGUF
Quantization vs Fu01978/Llama-3.2-3B-MoE-4Expert. mradermacher/Llama-3.2-3B-MoE-4Expert-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 85 tensors match exactly and 113 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, Attention 0/112, other 0/28