Garnet OCR 3B 0422 GGUF
For a convenient overview and download list, visit our model page for this model.
Model source
- Kind
- Other
- File size
- 808 MB–6.33 GB
- Base model
- prithivMLmods/Garnet-OCR-3B-0422
- Version
- vRevision e97fbbc
- Updated
- Nov 2, 2026
- Downloads
- 341
- Source
- Hugging Face
Source description
About
static quants of https://huggingface.co/prithivMLmods/Garnet-OCR-3B-0422
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Garnet-OCR-3B-0422-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)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | mmproj-Q8_0 | 0.9 | multi-modal supplement |
| GGUF | mmproj-f16 | 1.4 | multi-modal supplement |
| GGUF | Q2_K | 1.5 | |
| GGUF | Q3_K_S | 1.7 | |
| GGUF | Q3_K_M | 1.8 | lower quality |
| GGUF | Q3_K_L | 1.9 | |
| GGUF | IQ4_XS | 2.0 | |
| GGUF | Q4_K_S | 2.1 | fast, recommended |
| GGUF | Q4_K_M | 2.2 | fast, recommended |
| GGUF | Q5_K_S | 2.5 | |
| GGUF | Q5_K_M | 2.5 | |
| GGUF | Q6_K | 2.9 | very good quality |
| GGUF | Q8_0 | 3.7 | fast, best quality |
| GGUF | f16 | 6.9 | 16 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
Sources
1 sourceVerified Nov 2
Download files
Repository files
File inventory only; completeness is unverified.
- Garnet-OCR-3B-0422.IQ4_XS.gguf
- Garnet-OCR-3B-0422.Q2_K.gguf
- Garnet-OCR-3B-0422.Q3_K_L.gguf
- Garnet-OCR-3B-0422.Q3_K_M.gguf
- Garnet-OCR-3B-0422.Q3_K_S.gguf
- Garnet-OCR-3B-0422.Q4_K_M.gguf
- Garnet-OCR-3B-0422.Q4_K_S.gguf
- Garnet-OCR-3B-0422.Q5_K_M.gguf
- Garnet-OCR-3B-0422.Q5_K_S.gguf
- Garnet-OCR-3B-0422.Q6_K.gguf
- Garnet-OCR-3B-0422.Q8_0.gguf
- Garnet-OCR-3B-0422.f16.gguf
- Garnet-OCR-3B-0422.mmproj-Q8_0.gguf
- Garnet-OCR-3B-0422.mmproj-f16.gguf
Model artifacts
14 artifacts
Model artifacts
14 artifactsGarnet-OCR-3B-0422.IQ4_XS.gguf
gguf · 1.79 GB · SHA-256 213149569158…ee0e · Hugging Face
Download fileGarnet-OCR-3B-0422.mmproj-f16.gguf
gguf · 1.25 GB · SHA-256 f79b65e935f5…d4c8 · Hugging Face
Download fileGarnet-OCR-3B-0422.mmproj-Q8_0.gguf
gguf · Q8_0 (unverified) · 808 MB · SHA-256 f525c77afa39…d2af · Hugging Face
Download fileGarnet-OCR-3B-0422.Q2_K.gguf
gguf · Q2_K (unverified) · 1.28 GB · SHA-256 ce4a34a87bc2…9a32 · Hugging Face
Download fileGarnet-OCR-3B-0422.Q3_K_L.gguf
gguf · Q3_K_L (unverified) · 1.71 GB · SHA-256 bd3c84cc806a…32a0 · Hugging Face
Download fileGarnet-OCR-3B-0422.Q3_K_M.gguf
gguf · Q3_K_M (unverified) · 1.61 GB · SHA-256 56f2d9749b1d…8636 · Hugging Face
Download fileGarnet-OCR-3B-0422.Q3_K_S.gguf
gguf · Q3_K_S (unverified) · 1.48 GB · SHA-256 0c2abdf4437d…23ed · Hugging Face
Download fileGarnet-OCR-3B-0422.Q4_K_M.gguf
gguf · Q4_K_M (unverified) · 1.96 GB · SHA-256 f497b7d38cf1…2594 · Hugging Face
Download fileGarnet-OCR-3B-0422.Q4_K_S.gguf
gguf · Q4_K_S (unverified) · 1.87 GB · SHA-256 a8f777dae02a…52b0 · Hugging Face
Download fileGarnet-OCR-3B-0422.Q5_K_M.gguf
gguf · Q5_K_M (unverified) · 2.27 GB · SHA-256 9efdec20794a…bf0c · Hugging Face
Download fileGarnet-OCR-3B-0422.Q5_K_S.gguf
gguf · Q5_K_S (unverified) · 2.22 GB · SHA-256 3f5f5c777a7b…4808 · Hugging Face
Download fileGarnet-OCR-3B-0422.Q6_K.gguf
gguf · Q6_K (unverified) · 2.60 GB · SHA-256 a48dd8eabe79…041e · Hugging Face
Download fileGarnet-OCR-3B-0422.Q8_0.gguf
gguf · Q8_0 (unverified) · 3.37 GB · SHA-256 d4e4c5d621bc…b15a · Hugging Face
Download fileSource excerpts
3 excerpts
Source excerpts
3 excerpts--- base_model: prithivMLmods/Garnet-OCR-3B-0422 datasets: - prithivMLmods/OpenDoc-Pdf-Preview - prithivMLmods/Opendoc1-Analysis-Recognition - allenai/olmOCR-mix-0225 - prithivMLmods/Openpdf-Analysis-Recognition - prithivMLmods/OCR-Markdown-Dense-200x language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - text-generation-inference - Document - VLM - KIE - VL - Camel - Openpdf - Extraction - Linking - Markdown - Document Digitization - Intelligent Document Processing (IDP) - Intelligent Word Recognition (IWR) - pdf2markdown - image-to-text - ocr --- ## 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/prithivMLmods/Garnet-OCR-3B-0422 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Garnet-OCR-3B-0422-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/Garnet-OCR-3B-0422-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/Garnet-OCR-3B-0422-GGUF/resolve/main/Garnet-OCR-3B-0422.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/Garnet-OCR-3B-0422-GGUF/resolve/main/Garnet-OCR-3B-0422.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/Garnet-OCR-3B-0422-GGUF/resolve/main/Garnet-OCR-3B-0422.Q2_K.gguf) | Q2_K | 1.5 | | | [GGUF](https://huggingface.co/mradermacher/Garnet-OCR-3B-0422-GGUF/resolve/main/Garnet-OCR-3B-0422.Q3_K_S.gguf) | Q3_K_S | 1.7 | | | [GGUF](https://huggingface.co/mradermacher/Garnet-OCR-3B-0422-GGUF/resolve/main/Garnet-OCR-3B-0422.Q3_K_M.gguf)...
Source context: 341 downloads · 1 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/Garnet-OCR-3B-0422-GGUF
Source context: 712 downloads · 1 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/Garnet-OCR-3B-0422-GGUF
