This are the imatrix quantizations of the model LightOnOCR-1B-1025

Try to use the best quality you can run.
For the mmproj, try to use the F32 version as it will produce the best results. F32 > BF16 > F16

GGUF

Model size

0.8B params

Architecture

qwen3

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for noctrex/LightOnOCR-1B-1025-i1-GGUF

Base model

Quantized

(13)

this model