mradermacher/Mimma-3-12b-GGUF
Quantization (fewer layers) vs pankajmathur/Mimma-3-12b. mradermacher/Mimma-3-12b-GGUF matches part of pankajmathur/Mimma-3-12b (626 of its 1065 tensors; the rest of pankajmathur/Mimma-3-12b has no counterpart). On the shared part: mradermacher/Mimma-3-12b-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192