Interfaze

logo

Beta

pricing

docs

blog

sign in

LightOnOCR 2 1B GGUF

LightOnOCR 2 1B GGUF by noctrex, a image-to-text model with OCR capabilities. Understand and compare OCR features, benchmarks, and capabilities.

Comparison

FeatureLightOnOCR 2 1B GGUFInterfaze
Input Modalities

image

image, text, audio, video, document

Native OCRYesYes
Long Document ProcessingNoYes
Language Support

unknown

162+

Native Speech-to-TextNoYes
Native Object DetectionNoYes
Guardrail ControlsNoYes
Context Input Size

unknown

1M

Tool CallingNo

Tool calling supported + built in browser, code execution and web search

OCR Capabilities

FeatureLightOnOCR 2 1B GGUFInterfaze
Text Bounding BoxesNoYes
Confidence ScoresNoYes
Dense Image ProcessingNoYes
Low Quality ImagesNoYes
Handwritten TextNoYes
Charts, Tables & EquationsNoYes

Scaling

FeatureLightOnOCR 2 1B GGUFInterfaze
Scaling

Self-hosted/Provider-hosted with quantization

Unlimited

View model card on Hugging Face

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

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

Want more deterministic results?