nopesadly/GLM-OCR-Q4_K_M.gguf
Quantization (fewer layers) vs zai-org/GLM-OCR. nopesadly/GLM-OCR-Q4_K_M.gguf matches part of zai-org/GLM-OCR (179 of its 526 tensors; the rest of zai-org/GLM-OCR has no counterpart). On the shared part: nopesadly/GLM-OCR-Q4_K_M.gguf is a GGUF quantization (Q4_K_M) of the same weights: 72 tensors match exactly and 107 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/2, Norms 0/72, MLP 0/34, Attention 0/68, other 0/2