mradermacher/Magiq-3-GGUF
Quantization (fewer layers) vs mymaia/Magiq-3. mradermacher/Magiq-3-GGUF matches part of mymaia/Magiq-3 (227 of its 515 tensors; the rest of mymaia/Magiq-3 has no counterpart). On the shared part: mradermacher/Magiq-3-GGUF is a GGUF quantization (Q8_0) of the same weights: 97 tensors match exactly and 130 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, other 0/32, Attention 0/128