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-OCR2-1.5B-exp
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 ArtefakteNanonets-OCR2-1.5B-exp.i1-IQ1_M.gguf
gguf · 322 MB · SHA-256 439f5ff71137…c68d · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ1_S.gguf
gguf · 306 MB · SHA-256 9a1a7e5c234f…fd9f · Hugging Face
HerunterladenQuellenauszüge
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 | 0.4 | for the desperate |
| GGUF | i1-IQ1_M | 0.4 | mostly desperate |
| GGUF | i1-IQ2_XXS | 0.5 | |
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-OCR2-1.5B-exp.i1-IQ2_M.gguf
gguf · 396 MB · SHA-256 9702baa5cd3b…99f8 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ2_S.gguf
gguf · 376 MB · SHA-256 8a4b66699755…4add · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ2_XS.gguf
gguf · 368 MB · SHA-256 48d8138bd988…b7ca · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ2_XXS.gguf
gguf · 347 MB · SHA-256 671085898fd3…5110 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ3_M.gguf
gguf · 504 MB · SHA-256 c86e1dd014e0…0630 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ3_S.gguf
gguf · 496 MB · SHA-256 0f38a9449952…b0ed · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ3_XS.gguf
gguf · 479 MB · SHA-256 0f0a0f1ea1c4…b8ed · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ3_XXS.gguf
gguf · 432 MB · SHA-256 0245f47b7f1b…5a81 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ4_NL.gguf
gguf · 591 MB · SHA-256 58f80c0a73ca…1919 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-IQ4_XS.gguf
gguf · 569 MB · SHA-256 f3eeed2c75d3…e018 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q2_K_S.gguf
gguf · 430 MB · SHA-256 d76432563528…0b82 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q2_K.gguf
gguf · 449 MB · SHA-256 073d054c2ef6…1d1a · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q3_K_L.gguf
gguf · 560 MB · SHA-256 35df0803af93…d146 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q3_K_M.gguf
gguf · 531 MB · SHA-256 0a745d7fd00c…474d · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q3_K_S.gguf
gguf · 495 MB · SHA-256 73817fa73d8d…9b49 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q4_0.gguf
gguf · 592 MB · SHA-256 74af5cd0616c…c051 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q4_1.gguf
gguf · 635 MB · SHA-256 f1cd162162c3…b511 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q4_K_M.gguf
gguf · 618 MB · SHA-256 6faff3af26f5…ac29 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q4_K_S.gguf
gguf · 594 MB · SHA-256 c47cf6947171…54c5 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q5_K_M.gguf
gguf · 694 MB · SHA-256 9aa34cb59523…dd8a · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q5_K_S.gguf
gguf · 679 MB · SHA-256 759a94859327…2911 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.i1-Q6_K.gguf
gguf · 774 MB · SHA-256 606d69a709fd…ba93 · Hugging Face
HerunterladenNanonets-OCR2-1.5B-exp.imatrix.gguf
gguf · 1,13 MB · SHA-256 7560961035f6…52ff · Hugging Face
Herunterladen--- base_model: nanonets/Nanonets-OCR2-1.5B-exp language: - multilingual library_name: transformers license: apache-2.0 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-OCR2-1.5B-exp <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nanonets-OCR2-1.5B-exp-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Nanonets-OCR2-1.5B-exp-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Nanonets-OCR2-1.5B-exp-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-OCR2-1.5B-exp-i1-GGUF/resolve/main/Nanonets-OCR2-1.5B-exp.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-1.5B-exp-i1-GGUF/resolve/main/Nanonets-OCR2-1.5B-exp.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-1.5B-exp-i1-GGUF/resolve/main/Nanonets-OCR2-1.5B-exp.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-1.5B-exp-i1-GGUF/resolve/main/Nanonets-OCR2-1.5B-exp.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | | [GGUF](https://huggingface.co/mradermacher/Nanonets-OCR2-1.5B-exp-i1-GGUF/resolve/main/Nanonets-OCR2-1.5B-exp.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.5 | | | [GGUF](https://huggingfa...
Source context: 838 downloads · 0 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/Nanonets-OCR2-1.5B-exp-i1-GGUF
| i1-IQ2_XS |
| 0.5 |
| GGUF | i1-IQ2_S | 0.5 |
| GGUF | i1-IQ2_M | 0.5 |
| GGUF | i1-Q2_K_S | 0.6 | very low quality |
| GGUF | i1-IQ3_XXS | 0.6 | lower quality |
| GGUF | i1-Q2_K | 0.6 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XS | 0.6 |
| GGUF | i1-Q3_K_S | 0.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 0.6 | beats Q3_K* |
| GGUF | i1-IQ3_M | 0.6 |
| GGUF | i1-Q3_K_M | 0.7 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 0.7 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 0.7 |
| GGUF | i1-IQ4_NL | 0.7 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 0.7 | fast, low quality |
| GGUF | i1-Q4_K_S | 0.7 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 0.7 | fast, recommended |
| GGUF | i1-Q4_1 | 0.8 |
| GGUF | i1-Q5_K_S | 0.8 |
| GGUF | i1-Q5_K_M | 0.8 |
| GGUF | i1-Q6_K | 0.9 | practically like static Q6_K |
