π Model Description
pipeline_tag: image-to-text base_model: lightonai/LightOnOCR-2-1B
This are the quantizations of the model LightOnOCR-2-1B
Try to use the best quality you can run.
Quality order: BF16 > F16 > Q80 > Q6K > Q5KM > IQ4NL > IQ4XS > Q4KM
For the mmproj, try to use the F32 version as it will produce the best results.
Quality order: F32 > BF16 > F16
π GGUF File List
| π Filename | π¦ Size | β‘ Download |
|---|---|---|
|
LightOnOCR-2-1B-BF16.gguf
LFS
FP16
|
1.12 GB | Download |
|
LightOnOCR-2-1B-F16.gguf
LFS
FP16
|
1.12 GB | Download |
|
LightOnOCR-2-1B-IQ4_NL.gguf
LFS
Q4
|
363.89 MB | Download |
|
LightOnOCR-2-1B-IQ4_XS.gguf
LFS
Q4
|
350.76 MB | Download |
|
LightOnOCR-2-1B-Q4_K_M.gguf
Recommended
LFS
Q4
|
378.32 MB | Download |
|
LightOnOCR-2-1B-Q5_K_M.gguf
LFS
Q5
|
423.82 MB | Download |
|
LightOnOCR-2-1B-Q6_K.gguf
LFS
Q6
|
472.17 MB | Download |
|
LightOnOCR-2-1B-Q8_0.gguf
LFS
Q8
|
609.82 MB | Download |
|
imatrix.gguf
LFS
|
1.12 MB | Download |
|
mmproj-BF16.gguf
LFS
FP16
|
790.51 MB | Download |
|
mmproj-F16.gguf
LFS
FP16
|
781.36 MB | Download |
|
mmproj-F32.gguf
LFS
|
1.53 GB | Download |