Loading
Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
For a convenient overview and download list, visit our model page for this model.
Modellquelle
Quellenbeschreibung
weighted/imatrix quants of https://huggingface.co/nanonets/Nanonets-OCR2-3B
For a convenient overview and download list, visit our model page for this model.
static quants are available at
Quellen
1 QuelleVerifiziert 17. Sept.
Modellartefakte
25 ArtefakteQuellenauszüge
2 AuszügeThis is a vision model - mmproj files (if any) will be in the static repository.
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.
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | imatrix | 0.1 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 0.9 | for the desperate |
| GGUF | i1-IQ1_M | 1.0 | mostly desperate |
| GGUF | i1-IQ2_XXS | 1.0 | |
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
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
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.
Nanonets-OCR2-3B.i1-IQ2_M.gguf
gguf · 1,06 GB · SHA-256 e6044747ffb7…668f · Hugging Face
Nanonets-OCR2-3B.i1-IQ2_S.gguf
gguf · 1.013 MB · SHA-256 28e806b694f6…287b · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-IQ2_XS.gguf
gguf · 984 MB · SHA-256 2420d1c343d5…d5a0 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-IQ2_XXS.gguf
gguf · 904 MB · SHA-256 9ccaa3f131e6…75dc · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-IQ3_M.gguf
gguf · 1,39 GB · SHA-256 bc58a7a1e339…1336 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-IQ3_S.gguf
gguf · 1,36 GB · SHA-256 77344b480595…3feb · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-IQ3_XS.gguf
gguf · 1,30 GB · SHA-256 a0c0d515e724…b0c6 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-IQ3_XXS.gguf
gguf · 1,19 GB · SHA-256 83f5cae342e9…a781 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-IQ4_NL.gguf
gguf · 1,70 GB · SHA-256 a57f22e5077d…ff51 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-IQ4_XS.gguf
gguf · 1,62 GB · SHA-256 fc75b9964aaa…cff5 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-Q2_K_S.gguf
gguf · 1,12 GB · SHA-256 59a8a41b7904…ac24 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-Q3_K_L.gguf
gguf · 1,59 GB · SHA-256 d67f5012cb84…19b2 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-Q3_K_M.gguf
gguf · 1,48 GB · SHA-256 7c3e85383ce2…c683 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-Q3_K_S.gguf
gguf · 1,35 GB · SHA-256 8f580dabeec9…4a1a · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-Q4_K_M.gguf
gguf · 1,80 GB · SHA-256 6c6aacf879ca…1153 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-Q4_K_S.gguf
gguf · 1,71 GB · SHA-256 ee75ed476a5a…16a9 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-Q5_K_M.gguf
gguf · 2,07 GB · SHA-256 f23116d439c9…8491 · Hugging Face
HerunterladenNanonets-OCR2-3B.i1-Q5_K_S.gguf
gguf · 2,02 GB · SHA-256 57e721bb903e…6221 · Hugging Face
Herunterladen--- base_model: nanonets/Nanonets-OCR2-3B language: - multilingual library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - OCR - image-to-text - pdf2markdown - VQA --- ## 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/nanonets/Nanonets-OCR2-3B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nanonets-OCR2-3B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Nanonets-OCR2-3B-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Nanonets-OCR2-3B-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/Nanonets-OCR2-3B-i1-GGUF/resolve/main/Nanonets-OCR2-3B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-3B-i1-GGUF/resolve/main/Nanonets-OCR2-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-3B-i1-GGUF/resolve/main/Nanonets-OCR2-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-3B-i1-GGUF/resolve/main/Nanonets-OCR2-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-3B-i1-GGUF/resolve/main/Nanonets-OCR2-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-3B-i1-GGUF/resolve/main/Nanonets-OCR2-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | |...
Source context: 598 downloads · 0 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/Nanonets-OCR2-3B-i1-GGUF
| i1-IQ2_XS |
| 1.1 |
| GGUF | i1-IQ2_S | 1.2 |
| GGUF | i1-IQ2_M | 1.2 |
| GGUF | i1-Q2_K_S | 1.3 | very low quality |
| GGUF | i1-Q2_K | 1.4 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 1.4 | lower quality |
| GGUF | i1-IQ3_XS | 1.5 |
| GGUF | i1-Q3_K_S | 1.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 1.6 | beats Q3_K* |
| GGUF | i1-IQ3_M | 1.6 |
| GGUF | i1-Q3_K_M | 1.7 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 1.8 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 1.8 |
| GGUF | i1-IQ4_NL | 1.9 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 1.9 | fast, low quality |
| GGUF | i1-Q4_K_S | 1.9 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 2.0 | fast, recommended |
| GGUF | i1-Q4_1 | 2.1 |
| GGUF | i1-Q5_K_S | 2.3 |
| GGUF | i1-Q5_K_M | 2.3 |
| GGUF | i1-Q6_K | 2.6 | practically like static Q6_K |
