mradermacher/PowerMoE-3b-i1-GGUF
Quantization vs ibm-research/PowerMoE-3b. mradermacher/PowerMoE-3b-i1-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 97 tensors match exactly and 162 within quantization error.
Tensors changed: Embeddings 0/1, other 0/64, Norms 0/65, Attention 0/128, lm_head 0/1