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
static quants of https://huggingface.co/prithivMLmods/Megalodon-OCR-Sync-0713
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants are available at
Quellen
1 QuelleVerifiziert 17. Sept.
Modellartefakte
14 ArtefakteMegalodon-OCR-Sync-0713.f16.gguf
gguf · 5,75 GB · SHA-256 9cca649bc7bc…1a04 · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.IQ4_XS.gguf
gguf · 1,63 GB · SHA-256 1df9cf6dc272…383d · Hugging Face
HerunterladenQuellenauszüge
2 AuszügeIf 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 | mmproj-Q8_0 | 0.9 | multi-modal supplement |
| GGUF | Q2_K | 1.4 | |
| GGUF | mmproj-f16 | 1.4 | multi-modal supplement |
| GGUF | Q3_K_S | 1.6 | |
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.
Megalodon-OCR-Sync-0713.mmproj-f16.gguf
gguf · 1,25 GB · SHA-256 31cdf6095344…4a6d · Hugging Face
Megalodon-OCR-Sync-0713.mmproj-Q8_0.gguf
gguf · 806 MB · SHA-256 78fbfc60e888…af5f · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q2_K.gguf
gguf · 1,19 GB · SHA-256 9226baec8f7a…80c0 · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q3_K_L.gguf
gguf · 1,59 GB · SHA-256 f617e67a24ee…3af4 · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q3_K_M.gguf
gguf · 1,48 GB · SHA-256 45831bc9800f…c419 · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q3_K_S.gguf
gguf · 1,35 GB · SHA-256 71e98d88e540…42f2 · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q4_K_M.gguf
gguf · 1,80 GB · SHA-256 2679be1be0de…3da1 · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q4_K_S.gguf
gguf · 1,71 GB · SHA-256 894e0631eb5d…631f · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q5_K_M.gguf
gguf · 2,07 GB · SHA-256 b6bafa61b133…5ce3 · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q5_K_S.gguf
gguf · 2,02 GB · SHA-256 e5ef9ae858df…b63e · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q6_K.gguf
gguf · 2,36 GB · SHA-256 a52dbdd27260…b833 · Hugging Face
HerunterladenMegalodon-OCR-Sync-0713.Q8_0.gguf
gguf · 3,06 GB · SHA-256 7e3fb88a06e9…2faf · Hugging Face
Herunterladen--- base_model: prithivMLmods/Megalodon-OCR-Sync-0713 language: - en - zh library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - text-generation-inference - image-captioning - optical-character-recognition - intelligent-character-recognition - caption - ocr - visual-understanding - art - image-to-text - vlm - table --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/prithivMLmods/Megalodon-OCR-Sync-0713 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Megalodon-OCR-Sync-0713-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/Megalodon-OCR-Sync-0713-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/Megalodon-OCR-Sync-0713-GGUF/resolve/main/Megalodon-OCR-Sync-0713.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/Megalodon-OCR-Sync-0713-GGUF/resolve/main/Megalodon-OCR-Sync-0713.Q2_K.gguf) | Q2_K | 1.4 | | | [GGUF](https://huggingface.co/mradermacher/Megalodon-OCR-Sync-0713-GGUF/resolve/main/Megalodon-OCR-Sync-0713.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/Megalodon-OCR-Sync-0713-GGUF/resolve/main/Megalodon-OCR-Sync-0713.Q3_K_S.gguf) | Q3_K_S | 1.6 | | | [GGUF](https://huggingface.co/mradermacher/Megalodon-OCR-Sync-0713-GGUF/resolve/main/Megalodon-OCR-Sync-0713.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Megalodon-OCR-Sync-0713-GGUF/resolve/main/Megalodon-OCR-Sync-0713.Q3_K_L.gguf) | Q3_K_L | 1.8 | | | [GGUF](https://huggingface.co/mradermacher/Megalodon-OCR-Sync-0713-GGUF/resolve/main/Megalodon-OCR-Sync-0713.IQ4_XS.gguf) | IQ4_XS | 1.9 | | | [GGUF](https://huggingface.co/mra...
Source context: 249 downloads · 1 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/Megalodon-OCR-Sync-0713-GGUF
| Q3_K_M |
| 1.7 |
| lower quality |
| GGUF | Q3_K_L | 1.8 |
| GGUF | IQ4_XS | 1.9 |
| GGUF | Q4_K_S | 1.9 | fast, recommended |
| GGUF | Q4_K_M | 2.0 | fast, recommended |
| GGUF | Q5_K_S | 2.3 |
| GGUF | Q5_K_M | 2.3 |
| GGUF | Q6_K | 2.6 | very good quality |
| GGUF | Q8_0 | 3.4 | fast, best quality |
| GGUF | f16 | 6.3 | 16 bpw, overkill |
