Ir para o conteúdo

ModelListadosExterno

LightOnOCR 2 1B GGUF

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

Fontehuggingface.co/noctrex/LightOnOCR-2-1B-GGUF/tree/2c5eb6009ccfc10d7b12e99783d09b63a722405e

TipoOtherModelo baselightonai/LightOnOCR-2-1BVersãoRevision 2c5eb60

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 1,12 MB–1,53 GB
Modelo base: lightonai/LightOnOCR-2-1B
Versão: vRevision 2c5eb60
Atualizado: 25 de set. de 2026
Downloads: 1,4 mil
Tarefas: Legendas
Fonte: Hugging Face

Descrição da fonte

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

Fontes

1 fonte

Hugging FacePrimárioVersão 2c5eb6009ccfc10d7b12e99783d09b63a722405e

huggingface.co/noctrex/LightOnOCR-2-1B-GGUF/tree/2c5eb6009ccfc10d7b12e99783d09b63a722405e

Verificado 10 de set.

Artefatos de modelo

12 artefatos

imatrix.gguf

gguf · 1,12 MB · SHA-256 c790a393cf5f…d3f8 · Hugging Face

LightOnOCR-2-1B-BF16.gguf

gguf · 1,12 GB · SHA-256 72048ae42e60…e86d · Hugging Face

LightOnOCR-2-1B-F16.gguf

gguf · 1,12 GB · SHA-256 0cbee6bce16a…c5e7 · Hugging Face

LightOnOCR-2-1B-IQ4_NL.gguf

gguf · 364 MB · SHA-256 a0a5416d423c…cbbb · Hugging Face

LightOnOCR-2-1B-IQ4_XS.gguf

gguf · 351 MB · SHA-256 53d8be01ad75…7fc8 · Hugging Face

LightOnOCR-2-1B-Q4_K_M.gguf

gguf · 378 MB · SHA-256 de6fbbcf4ec1…992b · Hugging Face

LightOnOCR-2-1B-Q5_K_M.gguf

gguf · 424 MB · SHA-256 7faae1c49d77…37e8 · Hugging Face

LightOnOCR-2-1B-Q6_K.gguf

gguf · 472 MB · SHA-256 08a5a0ed57cf…5c3e · Hugging Face

LightOnOCR-2-1B-Q8_0.gguf

gguf · 610 MB · SHA-256 062cc44af0b9…f000 · Hugging Face

mmproj-BF16.gguf

gguf · 791 MB · SHA-256 b30a935ce0d3…9875 · Hugging Face

mmproj-F16.gguf

gguf · 781 MB · SHA-256 b016fb4fcfde…f2cb · Hugging Face

mmproj-F32.gguf

gguf · 1,53 GB · SHA-256 6288499e8f11…f828 · Hugging Face

Trechos de fonte

2 trechos

Readme10 de set.huggingface.co/noctrex/LightOnOCR-2-1B-GGUF

--- pipeline_tag: image-to-text base_model: lightonai/LightOnOCR-2-1B --- This are the quantizations of the model [LightOnOCR-2-1B](https://huggingface.co/lightonai/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

Note10 de set.huggingface.co/noctrex/LightOnOCR-2-1B-GGUF

Source context: 1392 downloads · 29 likes · Pipeline image-to-text · Repo noctrex/LightOnOCR-2-1B-GGUF