mradermacher/TinyDolphin-3x-MoE-i1-GGUF
Quantization vs jtatman/TinyDolphin-3x-MoE. mradermacher/TinyDolphin-3x-MoE-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 67 tensors match exactly and 90 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/45, other 0/22, Attention 0/88