Aller au contenu
ModelPrésentéExterne
Browse files

PaddleOCR VL 1.6 I1 GGUF

For a convenient overview and download list, visit our model page for this model.

Sourcehuggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF/tree/a7cb4fad03894bb94e59be7a9b4d607e9c39cd49
TypeModèleModèle de basePaddlePaddle/PaddleOCR-VL-1.6VersionRevision a7cb4faBClasse

Source du modèle

Type
Modèle
Taille du fichier
739 KB–367 MB
Modèle de base
PaddlePaddle/PaddleOCR-VL-1.6
Version
vRevision a7cb4fa
Mis à jour
30 oct. 2026
Téléchargements
878
Source
Hugging Face

Description de la source

About

weighted/imatrix quants of https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/PaddleOCR-VL-1.6-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

LinkTypeSize/GBNotes
GGUFimatrix0.1imatrix file (for creating your own quants)
GGUFi1-IQ1_S0.3for the desperate
GGUFi1-IQ1_M0.3mostly desperate
GGUFi1-IQ2_XXS0.3
GGUFi1-IQ2_XS0.3
GGUFi1-IQ2_S0.3
GGUFi1-IQ2_M0.3
GGUFi1-Q2_K_S0.3very low quality
GGUFi1-IQ3_XXS0.3lower quality
GGUFi1-Q2_K0.3IQ3_XXS probably better
GGUFi1-IQ3_XS0.3
GGUFi1-Q3_K_S0.3IQ3_XS probably better
GGUFi1-IQ3_S0.3beats Q3_K*
GGUFi1-IQ3_M0.4
GGUFi1-Q3_K_M0.4IQ3_S probably better
GGUFi1-Q3_K_L0.4IQ3_M probably better
GGUFi1-IQ4_XS0.4
GGUFi1-Q4_00.4fast, low quality
GGUFi1-IQ4_NL0.4prefer IQ4_XS
GGUFi1-Q4_K_S0.4optimal size/speed/quality
GGUFi1-Q4_K_M0.4fast, recommended
GGUFi1-Q4_10.4
GGUFi1-Q5_K_S0.4
GGUFi1-Q5_K_M0.4
GGUFi1-Q6_K0.5practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Sources

1 source
Hugging FacePrincipalVersion a7cb4fad03894bb94e59be7a9b4d607e9c39cd49
huggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF/tree/a7cb4fad03894bb94e59be7a9b4d607e9c39cd49

Vérifié 30 oct.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

25 artefacts

PaddleOCR-VL-1.6.i1-IQ1_M.gguf

gguf · 162 MB · SHA-256 1c2686584059…f406 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ1_S.gguf

gguf · 157 MB · SHA-256 91188f7b3a83…87a2 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ2_M.gguf

gguf · 199 MB · SHA-256 05797687196e…73f4 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ2_S.gguf

gguf · 193 MB · SHA-256 9104d032f509…7d3a · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ2_XS.gguf

gguf · 177 MB · SHA-256 620f25872dfd…6430 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ2_XXS.gguf

gguf · 169 MB · SHA-256 a5d927fceab9…63e0 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ3_M.gguf

gguf · 239 MB · SHA-256 60cb6534c42e…3c82 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ3_S.gguf

gguf · 234 MB · SHA-256 aa69f946536d…2e87 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ3_XS.gguf

gguf · 228 MB · SHA-256 9e5cee414822…a906 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ3_XXS.gguf

gguf · 208 MB · SHA-256 4ff538d45b73…7f3a · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ4_NL.gguf

gguf · 279 MB · SHA-256 8c8e518fa30a…8849 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-IQ4_XS.gguf

gguf · 269 MB · SHA-256 21a5257fd3bb…11d3 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q2_K_S.gguf

gguf · 201 MB · SHA-256 29c820de1aa9…ac37 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q2_K.gguf

gguf · 208 MB · SHA-256 e227c94dfbd2…4d35 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q3_K_L.gguf

gguf · 257 MB · SHA-256 df00aeb0f147…c1b8 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q3_K_M.gguf

gguf · 246 MB · SHA-256 fe74f55a1963…9532 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q3_K_S.gguf

gguf · 233 MB · SHA-256 b0fb61d1b0d7…6859 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q4_0.gguf

gguf · 279 MB · SHA-256 1e0df398f755…7a69 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q4_1.gguf

gguf · 300 MB · SHA-256 3b368a149dd7…b975 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q4_K_M.gguf

gguf · 286 MB · SHA-256 20da692aeb53…30aa · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q4_K_S.gguf

gguf · 280 MB · SHA-256 7d49c0fe7686…ee84 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q5_K_M.gguf

gguf · 326 MB · SHA-256 5be50e3b601e…99a6 · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q5_K_S.gguf

gguf · 322 MB · SHA-256 3d3d2655de43…baab · Hugging Face

Download file

PaddleOCR-VL-1.6.i1-Q6_K.gguf

gguf · 367 MB · SHA-256 86c6cee9c067…c4c0 · Hugging Face

Download file

PaddleOCR-VL-1.6.imatrix.gguf

gguf · 739 KB · SHA-256 0f424a70fca6…50ea · Hugging Face

Download file

Extraits de sources

3 extraits
Readme14 aoûthuggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF

--- base_model: PaddlePaddle/PaddleOCR-VL-1.6 language: - en - zh - multilingual library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - ERNIE4.5 - PaddleOCR - PaddlePaddle - image-to-text - ocr - document-parse - layout - table - formula - chart - seal - spotting --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> weighted/imatrix quants of https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PaddleOCR-VL-1.6-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/PaddleOCR-VL-1.6-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF/resolve/main/PaddleOCR-VL-1.6.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF/resolve/main/PaddleOCR-VL-1.6.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF/resolve/main/PaddleOCR-VL-1.6.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF/resolve/main/PaddleOCR-VL-1.6.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF/resolve/main/PaddleOCR-VL-1.6.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF/resolve/main/PaddleOCR-VL-1.6.i1-IQ2_S.gguf) | i1-IQ2_S | 0.3 | | | [GGUF](https://huggi...

Note30 oct.huggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF

Source context: 878 downloads · 2 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/PaddleOCR-VL-1.6-i1-GGUF

Note14 aoûthuggingface.co/mradermacher/PaddleOCR-VL-1.6-i1-GGUF

Source context: 857 downloads · 2 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/PaddleOCR-VL-1.6-i1-GGUF