---
pipeline_tag: image-to-text
base_model: lightonai/LightOnOCR-2-1B-ocr-soup
---
This are the quantizations of the model [LightOnOCR-2-1B-ocr-soup](https://huggingface.co/lightonai/LightOnOCR-2-1B-ocr-soup)

Try to use the best quality you can run.  

Quality order: BF16 > F16 > Q8_0 > Q6_K > Q5_K_M > IQ4_NL > IQ4_XS > Q4_K_M

For the mmproj, try to use the F32 version as it will produce the best results.  
Quality order: F32 > BF16 > F16