Lamapi/next-ocr-Q4_K_M-GGUF
Quantization (fewer layers) vs thelamapi/next-ocr. Lamapi/next-ocr-Q4_K_M-GGUF matches part of thelamapi/next-ocr (399 of its 750 tensors; the rest of thelamapi/next-ocr has no counterpart). On the shared part: Lamapi/next-ocr-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1