mradermacher/MiLMMT-46-12B-v1.0-GGUF
Quantization (fewer layers) vs xiaomi-research/MiLMMT-46-12B-v1.0. mradermacher/MiLMMT-46-12B-v1.0-GGUF matches part of xiaomi-research/MiLMMT-46-12B-v1.0 (626 of its 1065 tensors; the rest of xiaomi-research/MiLMMT-46-12B-v1.0 has no counterpart). On the shared part: mradermacher/MiLMMT-46-12B-v1.0-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