mradermacher/cali3-12b-06-GGUF
Quantization (fewer layers) vs jayanthanc/cali3-12b-06. mradermacher/cali3-12b-06-GGUF matches part of jayanthanc/cali3-12b-06 (626 of its 1065 tensors; the rest of jayanthanc/cali3-12b-06 has no counterpart). On the shared part: mradermacher/cali3-12b-06-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