Ir para o conteúdo
ModelListadosExterno
Browse files

Fast PaddleOCR VL 1.5 I1 GGUF

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

TipoOtherModelo baseandynoodles/Fast-PaddleOCR-VL-1.5VersãoRevision 6235a54Bnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
739 KB–367 MB
Modelo base
andynoodles/Fast-PaddleOCR-VL-1.5
Versão
vRevision 6235a54
Atualizado
2 de nov. de 2026
Downloads
517
Fonte
Hugging Face

Descrição da fonte

About

weighted/imatrix quants of https://huggingface.co/andynoodles/Fast-PaddleOCR-VL-1.5

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

static quants are available at https://huggingface.co/mradermacher/Fast-PaddleOCR-VL-1.5-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.

Fontes

1 fonte
Hugging FacePrimárioVersão 6235a54ce1e9738e07f11f5e8680094a28cf7602
huggingface.co/mradermacher/Fast-PaddleOCR-VL-1.5-i1-GGUF/tree/6235a54ce1e9738e07f11f5e8680094a28cf7602

Verificado 2 de nov.

Download files

Artefatos de modelo

25 artefatos

Fast-PaddleOCR-VL-1.5.i1-IQ1_M.gguf

gguf · 162 MB · SHA-256 701ce845e30f…dc9d · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ1_S.gguf

gguf · 157 MB · SHA-256 6dd0ac0f35b7…1be9 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ2_M.gguf

gguf · 199 MB · SHA-256 aff52e3b6a0a…93bc · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ2_S.gguf

gguf · 193 MB · SHA-256 183978f4a078…6ff4 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ2_XS.gguf

gguf · 177 MB · SHA-256 72a83b1326e0…945d · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ2_XXS.gguf

gguf · 169 MB · SHA-256 aeafc022721f…f381 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ3_M.gguf

gguf · 239 MB · SHA-256 99da534f5e78…79ba · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ3_S.gguf

gguf · 234 MB · SHA-256 f0999f74a087…a808 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ3_XS.gguf

gguf · 228 MB · SHA-256 259800aea62c…2f7b · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ3_XXS.gguf

gguf · 208 MB · SHA-256 43ac99795ad2…a9c4 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ4_NL.gguf

gguf · 279 MB · SHA-256 bba96a70153d…7ec0 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-IQ4_XS.gguf

gguf · 269 MB · SHA-256 330d8296fa3e…acc0 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q2_K_S.gguf

gguf · Q2_K_S (unverified) · 201 MB · SHA-256 fdc346440f7b…1a19 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q2_K.gguf

gguf · Q2_K (unverified) · 208 MB · SHA-256 711797349a6a…ec84 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q3_K_L.gguf

gguf · Q3_K_L (unverified) · 257 MB · SHA-256 d66d0bf73317…bf24 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q3_K_M.gguf

gguf · Q3_K_M (unverified) · 246 MB · SHA-256 4e5dc3699bdb…c548 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q3_K_S.gguf

gguf · Q3_K_S (unverified) · 233 MB · SHA-256 42f0cb9b47a7…d07a · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q4_0.gguf

gguf · Q4_0 (unverified) · 279 MB · SHA-256 9100c576e8ac…8397 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q4_1.gguf

gguf · Q4_1 (unverified) · 300 MB · SHA-256 a5f02317ba2c…f57a · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q4_K_M.gguf

gguf · Q4_K_M (unverified) · 286 MB · SHA-256 31f080e1ca94…05f0 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q4_K_S.gguf

gguf · Q4_K_S (unverified) · 280 MB · SHA-256 3b45d6fa17a6…d5ce · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q5_K_M.gguf

gguf · Q5_K_M (unverified) · 326 MB · SHA-256 9ffc8342c417…151f · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q5_K_S.gguf

gguf · Q5_K_S (unverified) · 322 MB · SHA-256 596fb6f4534a…f853 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.i1-Q6_K.gguf

gguf · Q6_K (unverified) · 367 MB · SHA-256 5d7678f953ce…c4d9 · Hugging Face

Download file

Fast-PaddleOCR-VL-1.5.imatrix.gguf

gguf · 739 KB · SHA-256 4c2e342df051…81a7 · Hugging Face

Download file

Trechos de fonte

3 trechos

--- base_model: andynoodles/Fast-PaddleOCR-VL-1.5 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/andynoodles/Fast-PaddleOCR-VL-1.5 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Fast-PaddleOCR-VL-1.5-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Fast-PaddleOCR-VL-1.5-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/Fast-PaddleOCR-VL-1.5-i1-GGUF/resolve/main/Fast-PaddleOCR-VL-1.5.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Fast-PaddleOCR-VL-1.5-i1-GGUF/resolve/main/Fast-PaddleOCR-VL-1.5.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Fast-PaddleOCR-VL-1.5-i1-GGUF/resolve/main/Fast-PaddleOCR-VL-1.5.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Fast-PaddleOCR-VL-1.5-i1-GGUF/resolve/main/Fast-PaddleOCR-VL-1.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | | | [GGUF](https://huggingface.co/mradermacher/Fast-PaddleOCR-VL-1.5-i1-GGUF/resolve/main/Fast-PaddleOCR-VL-1.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | | | [GGUF](https://huggingface.co/mradermacher/Fast-PaddleOCR-VL-1.5-i1-GGUF/resolve/main/Fa...

Source context: 517 downloads · 0 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/Fast-PaddleOCR-VL-1.5-i1-GGUF

Source context: 234 downloads · 0 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/Fast-PaddleOCR-VL-1.5-i1-GGUF