cstr/glm-ocr-crispembed-GGUF
Not comparable yet vs zai-org/glm-edge-v-2b. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 685/526 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs zai-org/glm-edge-v-2b. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 685/526 match), usually an architecture llama.cpp's name map doesn't cover yet.