cstr/lightonocr-GGUF
Not comparable yet vs lightonai/LightOnOCR-2-1B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (6 of 532/532 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs lightonai/LightOnOCR-2-1B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (6 of 532/532 match), usually an architecture llama.cpp's name map doesn't cover yet.