HunyuanOCR GGUF
tencent-hunyuan-community
Modellquelle
- Art
- Other
- Dateigröße
- 248 MB–1,01 GB
- Basismodell
- tencent/HunyuanOCR
- Version
- vRevision 064e0f1
- Aktualisiert
- 5. Nov. 2026
- Downloads
- 991
- Quelle
- Hugging Face
Quellenbeschreibung
About
static quants of https://huggingface.co/tencent/HunyuanOCR
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants are available at https://huggingface.co/mradermacher/HunyuanOCR-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 | Q2_K | 0.4 | |
| GGUF | Q3_K_S | 0.4 | |
| GGUF | Q3_K_M | 0.4 | lower quality |
| GGUF | Q3_K_L | 0.4 | |
| GGUF | IQ4_XS | 0.4 | |
| GGUF | Q4_K_S | 0.4 | fast, recommended |
| GGUF | Q4_K_M | 0.5 | fast, recommended |
| GGUF | Q5_K_S | 0.5 | |
| GGUF | Q5_K_M | 0.5 | |
| GGUF | Q6_K | 0.5 | very good quality |
| GGUF | Q8_0 | 0.7 | fast, best quality |
| GGUF | mmproj-Q8_0 | 0.8 | multi-modal supplement |
| GGUF | mmproj-f16 | 1.1 | multi-modal supplement |
| GGUF | f16 | 1.2 | 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.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 5. Nov.
Download files
Repository files
File inventory only; completeness is unverified.
- HunyuanOCR.IQ4_XS.gguf
- HunyuanOCR.Q2_K.gguf
- HunyuanOCR.Q3_K_L.gguf
- HunyuanOCR.Q3_K_M.gguf
- HunyuanOCR.Q3_K_S.gguf
- HunyuanOCR.Q4_K_M.gguf
- HunyuanOCR.Q4_K_S.gguf
- HunyuanOCR.Q5_K_M.gguf
- HunyuanOCR.Q5_K_S.gguf
- HunyuanOCR.Q6_K.gguf
- HunyuanOCR.Q8_0.gguf
- HunyuanOCR.f16.gguf
- HunyuanOCR.mmproj-Q8_0.gguf
- HunyuanOCR.mmproj-f16.gguf
Modellartefakte
14 Artefakte
Modellartefakte
14 ArtefakteHunyuanOCR.mmproj-Q8_0.gguf
gguf · Q8_0 (unverified) · 699 MB · SHA-256 eb7fc35fcbac…2601 · Hugging Face
Download fileHunyuanOCR.Q2_K.gguf
gguf · Q2_K (unverified) · 248 MB · SHA-256 faf627a5134e…64ba · Hugging Face
Download fileHunyuanOCR.Q3_K_L.gguf
gguf · Q3_K_L (unverified) · 312 MB · SHA-256 a445ae98522b…3c59 · Hugging Face
Download fileHunyuanOCR.Q3_K_M.gguf
gguf · Q3_K_M (unverified) · 293 MB · SHA-256 d82aed19094b…283e · Hugging Face
Download fileHunyuanOCR.Q3_K_S.gguf
gguf · Q3_K_S (unverified) · 272 MB · SHA-256 b44649df28d7…725b · Hugging Face
Download fileHunyuanOCR.Q4_K_M.gguf
gguf · Q4_K_M (unverified) · 339 MB · SHA-256 ee2378d06e4b…8bed · Hugging Face
Download fileHunyuanOCR.Q4_K_S.gguf
gguf · Q4_K_S (unverified) · 326 MB · SHA-256 1326cedb90dd…3274 · Hugging Face
Download fileHunyuanOCR.Q5_K_M.gguf
gguf · Q5_K_M (unverified) · 381 MB · SHA-256 69df7c5d61aa…b726 · Hugging Face
Download fileHunyuanOCR.Q5_K_S.gguf
gguf · Q5_K_S (unverified) · 374 MB · SHA-256 e4e01cf5a1e0…be81 · Hugging Face
Download fileHunyuanOCR.Q6_K.gguf
gguf · Q6_K (unverified) · 427 MB · SHA-256 a60dde791fab…4e13 · Hugging Face
Download fileHunyuanOCR.Q8_0.gguf
gguf · Q8_0 (unverified) · 551 MB · SHA-256 2ff79d146bda…a947 · Hugging Face
Download fileQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: tencent/HunyuanOCR language: - multilingual library_name: transformers license: other mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - ocr - hunyuan - vision-language - image-to-text - 1B - end-to-end --- ## 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/tencent/HunyuanOCR <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#HunyuanOCR-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/HunyuanOCR-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/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.Q2_K.gguf) | Q2_K | 0.4 | | | [GGUF](https://huggingface.co/mradermacher/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.Q3_K_S.gguf) | Q3_K_S | 0.4 | | | [GGUF](https://huggingface.co/mradermacher/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.Q3_K_L.gguf) | Q3_K_L | 0.4 | | | [GGUF](https://huggingface.co/mradermacher/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.IQ4_XS.gguf) | IQ4_XS | 0.4 | | | [GGUF](https://huggingface.co/mradermacher/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.Q5_K_S.gguf) | Q5_K_S | 0.5 | | | [GGUF](https://huggingface.co/mradermacher/HunyuanOCR-GGUF/resolve/main/HunyuanOCR.Q5_K_M.gguf) | Q5_K_M | 0.5 | | | [GGUF](https://huggingfac...
Source context: 2170 downloads · 1 likes · Library transformers · Repo mradermacher/HunyuanOCR-GGUF
Source context: 991 downloads · 1 likes · Library transformers · Repo mradermacher/HunyuanOCR-GGUF
