42ailab/Logics-Parsing-v2-GGUF
Quantization (fewer layers) vs Logics-MLLM/Logics-Parsing-v2. 42ailab/Logics-Parsing-v2-GGUF matches part of Logics-MLLM/Logics-Parsing-v2 (398 of its 713 tensors; the rest of Logics-MLLM/Logics-Parsing-v2 has no counterpart). On the shared part: 42ailab/Logics-Parsing-v2-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 253 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144