matthewdubois
/

GLM-OCR-3bit-mlx

Image-Text-to-Text

Model card Files Files and versions

GLM-OCR-3bit-mlx / processor_config.json

Commit History

Mixed quantization: 3-bit LM + 8-bit vision encoder (728MB, 34% smaller)

8001df4
verified

matthewdubois commited on 13 days ago

Fix processor_class to GlmOcrProcessor in processor_config.json

a0299ac
verified

matthewdubois commited on 14 days ago

GLM-OCR 3-bit quantized MLX model for business card OCR

b71374d
verified

matthewdubois commited on 14 days ago