Skip to content
ModelListedExternal
Browse files

Dots.ocr GGUF

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

Sourcehuggingface.co/mradermacher/dots.ocr-GGUF/tree/722cab81d49404800b38d0b83be3862d7519e704
KindOtherBase modeldots-studio/dots.ocrVersionRevision 722cab8Bgrade

Model source

Kind
Other
File size
718 MB–3.32 GB
Base model
dots-studio/dots.ocr
Version
vRevision 722cab8
Updated
Sep 15, 2026
Downloads
708
Source
Hugging Face

Source description

About

static quants of https://huggingface.co/dots-studio/dots.ocr

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/dots.ocr-i1-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
GGUFQ2_K0.9
GGUFQ3_K_S1.0
GGUFQ3_K_M1.0lower quality
GGUFQ3_K_L1.1
GGUFIQ4_XS1.1
GGUFQ4_K_S1.2fast, recommended
GGUFQ4_K_M1.2fast, recommended
GGUFQ5_K_S1.4
GGUFQ5_K_M1.4
GGUFmmproj-Q8_01.4multi-modal supplement
GGUFQ6_K1.6very good quality
GGUFQ8_02.0fast, best quality
GGUFmmproj-f162.6multi-modal supplement
GGUFf163.716 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 722cab81d49404800b38d0b83be3862d7519e704
huggingface.co/mradermacher/dots.ocr-GGUF/tree/722cab81d49404800b38d0b83be3862d7519e704

Verified Aug 20

Download files

Model artifacts

14 artifacts

dots.ocr.f16.gguf

gguf · 3.32 GB · SHA-256 6aaed54f013e…ae0b · Hugging Face

Download file

dots.ocr.IQ4_XS.gguf

gguf · 979 MB · SHA-256 8b26f18dcf7e…2478 · Hugging Face

Download file

dots.ocr.mmproj-f16.gguf

gguf · 2.35 GB · SHA-256 2d62c851cd20…714e · Hugging Face

Download file

dots.ocr.mmproj-Q8_0.gguf

gguf · 1.25 GB · SHA-256 ef820624ff0c…9716 · Hugging Face

Download file

dots.ocr.Q2_K.gguf

gguf · 718 MB · SHA-256 fe2f149757dc…ed39 · Hugging Face

Download file

dots.ocr.Q3_K_L.gguf

gguf · 935 MB · SHA-256 0ca492072a85…c2ec · Hugging Face

Download file

dots.ocr.Q3_K_M.gguf

gguf · 882 MB · SHA-256 3129f804bf97…bdc0 · Hugging Face

Download file

dots.ocr.Q3_K_S.gguf

gguf · 821 MB · SHA-256 7d00f86cfbff…488d · Hugging Face

Download file

dots.ocr.Q4_K_M.gguf

gguf · 1.04 GB · SHA-256 f5b196c49210…8a6e · Hugging Face

Download file

dots.ocr.Q4_K_S.gguf

gguf · 1,022 MB · SHA-256 fa5da019a534…41af · Hugging Face

Download file

dots.ocr.Q5_K_M.gguf

gguf · 1.20 GB · SHA-256 0dec7a9d8c1e…eaa0 · Hugging Face

Download file

dots.ocr.Q5_K_S.gguf

gguf · 1.17 GB · SHA-256 a64982c02053…d037 · Hugging Face

Download file

dots.ocr.Q6_K.gguf

gguf · 1.36 GB · SHA-256 72de04dc260c…fcb3 · Hugging Face

Download file

dots.ocr.Q8_0.gguf

gguf · 1.76 GB · SHA-256 de3dbc325c17…461a · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 20huggingface.co/mradermacher/dots.ocr-GGUF

--- base_model: dots-studio/dots.ocr language: - en - zh - multilingual library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - image-to-text - ocr - document-parse - layout - table - formula - transformers - custom_code --- ## 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/dots-studio/dots.ocr <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#dots.ocr-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/dots.ocr-i1-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/dots.ocr-GGUF/resolve/main/dots.ocr.Q2_K.gguf) | Q2_K | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/dots.ocr-GGUF/resolve/main/dots.ocr.Q3_K_S.gguf) | Q3_K_S | 1.0 | | | [GGUF](https://huggingface.co/mradermacher/dots.ocr-GGUF/resolve/main/dots.ocr.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/dots.ocr-GGUF/resolve/main/dots.ocr.Q3_K_L.gguf) | Q3_K_L | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/dots.ocr-GGUF/resolve/main/dots.ocr.IQ4_XS.gguf) | IQ4_XS | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/dots.ocr-GGUF/resolve/main/dots.ocr.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/dots.ocr-GGUF/resolve/main/dots.ocr.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/dots.ocr-GGUF/resolve/main/dots.ocr.Q5_K_S.gguf) | Q5_K_S | 1.4 | | | [GGUF](https://huggingface.co/mradermacher/dots.ocr-GGUF/resolve/main/dots.ocr.Q5_K_M.gguf) | Q5_K_M | 1.4 | | | [GGUF](https://huggingface...

NoteAug 20huggingface.co/mradermacher/dots.ocr-GGUF

Source context: 708 downloads · 3 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/dots.ocr-GGUF