These are quantizations of the model Chandra-OCR
Original model: https://huggingface.co/datalab-to/chandra
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
- Downloads last month
- 13,056
Hardware compatibility
Log In
to view the estimation
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Model tree for noctrex/Chandra-OCR-GGUF
Base model
datalab-to/chandra