0xSero / GLM-5.2-REAP-504B-GGUF

GGUF builds of the 34%-expert-pruned, Router-KD-recovered GLM-5.2-504B — for llama.cpp (CPU / Metal / CUDA). Includes the first working GGUF of a GLM-5.2 DSA model, made possible by a custom patch for its shared sparse-attention indexer.