Skip to content

ModelListedExternal

LightOnOCR 2 1B Ocr Soup GGUF

This are the quantizations of the model LightOnOCR-2-1B-ocr-soup

Sourcehuggingface.co/noctrex/LightOnOCR-2-1B-ocr-soup-GGUF/tree/a683d3cac5f26cc2039d117528d3e04e400bad56

KindOtherBase modellightonai/LightOnOCR-2-1B-ocr-soupVersionRevision a683d3c

Model source

Kind: Other
File size: 1.12 MB–1.53 GB
Base model: lightonai/LightOnOCR-2-1B-ocr-soup
Version: vRevision a683d3c
Updated: Sep 26, 2026
Downloads: 4.1K
Tasks: Captioning
Source: Hugging Face

Source description

This are the quantizations of the model 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

Sources

1 source

Hugging FacePrimaryVersion a683d3cac5f26cc2039d117528d3e04e400bad56

huggingface.co/noctrex/LightOnOCR-2-1B-ocr-soup-GGUF/tree/a683d3cac5f26cc2039d117528d3e04e400bad56

Verified Sep 10

Model artifacts

12 artifacts

imatrix.gguf

gguf · 1.12 MB · SHA-256 c2fc0461020a…5489 · Hugging Face

LightOnOCR-2-1B-ocr-soup-BF16.gguf

gguf · 1.12 GB · SHA-256 9540a7e48678…96af · Hugging Face

LightOnOCR-2-1B-ocr-soup-F16.gguf

gguf · 1.12 GB · SHA-256 11a26bcc98d4…b604 · Hugging Face

LightOnOCR-2-1B-ocr-soup-IQ4_NL.gguf

gguf · 364 MB · SHA-256 b9998f1a251b…fad3 · Hugging Face

LightOnOCR-2-1B-ocr-soup-IQ4_XS.gguf

gguf · 351 MB · SHA-256 373b69aa3b47…0040 · Hugging Face

LightOnOCR-2-1B-ocr-soup-Q4_K_M.gguf

gguf · 378 MB · SHA-256 6bdf9fdc6ef7…bc3b · Hugging Face

LightOnOCR-2-1B-ocr-soup-Q5_K_M.gguf

gguf · 424 MB · SHA-256 2055ba681239…0b2f · Hugging Face

LightOnOCR-2-1B-ocr-soup-Q6_K.gguf

gguf · 472 MB · SHA-256 48d2d2611650…6a33 · Hugging Face

LightOnOCR-2-1B-ocr-soup-Q8_0.gguf

gguf · 610 MB · SHA-256 64f314b08acd…3dea · Hugging Face

mmproj-BF16.gguf

gguf · 791 MB · SHA-256 2d7d96c97662…e8c1 · Hugging Face

mmproj-F16.gguf

gguf · 781 MB · SHA-256 fefd91bc5551…778b · Hugging Face

mmproj-F32.gguf

gguf · 1.53 GB · SHA-256 e2ec8e8dc4ae…cf55 · Hugging Face

Source excerpts

2 excerpts

ReadmeSep 10huggingface.co/noctrex/LightOnOCR-2-1B-ocr-soup-GGUF

--- 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

NoteSep 10huggingface.co/noctrex/LightOnOCR-2-1B-ocr-soup-GGUF

Source context: 4115 downloads · 10 likes · Pipeline image-to-text · Repo noctrex/LightOnOCR-2-1B-ocr-soup-GGUF