Skip to content
ModelListedExternal
Download

PaddleOCR VL 0.9B GGUF

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

Sourcehuggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF/tree/97374cac5a20f375a695ea33eac7f0589be41fda
KindOtherBase modellvyufeng/PaddleOCR-VL-0.9BVersionRevision 97374ca

Model source

Kind
Other
File size
208–892 MB
Base model
lvyufeng/PaddleOCR-VL-0.9B
Version
vRevision 97374ca
Updated
Sep 26, 2026
Downloads
371
Tasks
Captioning
Source
Hugging Face

Source description

About

static quants of https://huggingface.co/lvyufeng/PaddleOCR-VL-0.9B

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

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

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
GGUFQ2_K0.3
GGUFQ3_K_S0.3
GGUFQ3_K_M0.4lower quality
GGUFQ3_K_L0.4
GGUFIQ4_XS0.4
GGUFQ4_K_S0.4fast, recommended
GGUFQ4_K_M0.4fast, recommended
GGUFQ5_K_S0.4
GGUFQ5_K_M0.4
GGUFQ6_K0.5very good quality
GGUFQ8_00.6fast, best quality
GGUFf161.016 bpw, overkill

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.

Sources

1 source
Hugging FacePrimaryVersion 97374cac5a20f375a695ea33eac7f0589be41fda
huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF/tree/97374cac5a20f375a695ea33eac7f0589be41fda

Verified Sep 11

Model artifacts

12 artifacts

PaddleOCR-VL-0.9B.f16.gguf

gguf · 892 MB · SHA-256 3a494335be24…186d · Hugging Face

Download

PaddleOCR-VL-0.9B.IQ4_XS.gguf

gguf · 270 MB · SHA-256 a0c706713de4…69d7 · Hugging Face

Download

PaddleOCR-VL-0.9B.Q2_K.gguf

gguf · 208 MB · SHA-256 634571bb60fe…7c67 · Hugging Face

Download

PaddleOCR-VL-0.9B.Q3_K_L.gguf

gguf · 257 MB · SHA-256 5b22c36967c7…6f7c · Hugging Face

Download

PaddleOCR-VL-0.9B.Q3_K_M.gguf

gguf · 246 MB · SHA-256 c2e45eb844db…23d2 · Hugging Face

Download

PaddleOCR-VL-0.9B.Q3_K_S.gguf

gguf · 233 MB · SHA-256 2f95cbc236f7…d9ac · Hugging Face

Download

PaddleOCR-VL-0.9B.Q4_K_M.gguf

gguf · 286 MB · SHA-256 7f50f35be0b7…c39f · Hugging Face

Download

PaddleOCR-VL-0.9B.Q4_K_S.gguf

gguf · 280 MB · SHA-256 08e4366d6261…db4f · Hugging Face

Download

PaddleOCR-VL-0.9B.Q5_K_M.gguf

gguf · 326 MB · SHA-256 f182705413cb…3b82 · Hugging Face

Download

PaddleOCR-VL-0.9B.Q5_K_S.gguf

gguf · 322 MB · SHA-256 5913fd906b40…7cf8 · Hugging Face

Download

PaddleOCR-VL-0.9B.Q6_K.gguf

gguf · 367 MB · SHA-256 b5d5ab223097…41c9 · Hugging Face

Download

PaddleOCR-VL-0.9B.Q8_0.gguf

gguf · 475 MB · SHA-256 2abd2172750f…4dfa · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 11huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF

--- base_model: lvyufeng/PaddleOCR-VL-0.9B language: - en - zh - multilingual library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - pytorch - transformers - mindspore - mindnlp - ERNIE4.5 - image-to-text - ocr - document-parse - layout - table - formula - chart --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/lvyufeng/PaddleOCR-VL-0.9B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PaddleOCR-VL-0.9B-GGUF).*** weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## 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-0.9B-GGUF/resolve/main/PaddleOCR-VL-0.9B.Q2_K.gguf) | Q2_K | 0.3 | | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF/resolve/main/PaddleOCR-VL-0.9B.Q3_K_S.gguf) | Q3_K_S | 0.3 | | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF/resolve/main/PaddleOCR-VL-0.9B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF/resolve/main/PaddleOCR-VL-0.9B.Q3_K_L.gguf) | Q3_K_L | 0.4 | | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF/resolve/main/PaddleOCR-VL-0.9B.IQ4_XS.gguf) | IQ4_XS | 0.4 | | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF/resolve/main/PaddleOCR-VL-0.9B.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF/resolve/m...

NoteSep 11huggingface.co/mradermacher/PaddleOCR-VL-0.9B-GGUF

Source context: 371 downloads · 2 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/PaddleOCR-VL-0.9B-GGUF