Saltar al contenido
ModelPublicadoExterno
Browse files

CoE SlideVQA 8B I1 GGUF

For a convenient overview and download list, visit our model page for this model.

Fuentehuggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF/tree/84202eccd83ab67de642b80e7e80ded927daed04
TipoOtherModelo basePeiyangLiu/CoE-SlideVQA-8BVersiónRevision 84202ecBcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
5,10 MB–6,26 GB
Modelo base
PeiyangLiu/CoE-SlideVQA-8B
Versión
vRevision 84202ec
Actualizado
10 oct 2026
Descargas
859
Fuente
Hugging Face

Descripción de la fuente

About

weighted/imatrix quants of https://huggingface.co/PeiyangLiu/CoE-SlideVQA-8B

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/CoE-SlideVQA-8B-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

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)

LinkTypeSize/GBNotes
GGUFimatrix0.1imatrix file (for creating your own quants)
GGUFi1-IQ1_S2.2for the desperate
GGUFi1-IQ1_M2.4mostly desperate
GGUFi1-IQ2_XXS2.6
GGUFi1-IQ2_XS2.8
GGUFi1-IQ2_S3.0
GGUFi1-IQ2_M3.2
GGUFi1-Q2_K_S3.2very low quality
GGUFi1-Q2_K3.4IQ3_XXS probably better
GGUFi1-IQ3_XXS3.5lower quality
GGUFi1-IQ3_XS3.7
GGUFi1-Q3_K_S3.9IQ3_XS probably better
GGUFi1-IQ3_S3.9beats Q3_K*
GGUFi1-IQ3_M4.0
GGUFi1-Q3_K_M4.2IQ3_S probably better
GGUFi1-Q3_K_L4.5IQ3_M probably better
GGUFi1-IQ4_XS4.7
GGUFi1-Q4_04.9fast, low quality
GGUFi1-IQ4_NL4.9prefer IQ4_XS
GGUFi1-Q4_K_S4.9optimal size/speed/quality
GGUFi1-Q4_K_M5.1fast, recommended
GGUFi1-Q4_15.3
GGUFi1-Q5_K_S5.8
GGUFi1-Q5_K_M6.0
GGUFi1-Q6_K6.8practically like static Q6_K

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. 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.

Fuentes

1 fuente
Hugging FacePrincipalVersión 84202eccd83ab67de642b80e7e80ded927daed04
huggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF/tree/84202eccd83ab67de642b80e7e80ded927daed04

Verificado 10 oct

Download files

Artefactos del modelo

25 artefactos

CoE-SlideVQA-8B.i1-IQ1_M.gguf

gguf · 2,10 GB · SHA-256 9d59cfc65858…d992 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ1_S.gguf

gguf · 1,97 GB · SHA-256 680ebc36a6f6…108f · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ2_M.gguf

gguf · 2,84 GB · SHA-256 e859d49f90b4…b093 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ2_S.gguf

gguf · 2,67 GB · SHA-256 c657191c54fd…04ed · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ2_XS.gguf

gguf · 2,51 GB · SHA-256 51425e1ba8a2…7ef5 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ2_XXS.gguf

gguf · 2,32 GB · SHA-256 059edb2b1d08…abb9 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ3_M.gguf

gguf · 3,63 GB · SHA-256 0705e907a3cb…bd7b · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ3_S.gguf

gguf · 3,53 GB · SHA-256 7617c4ad7d89…b39c · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ3_XS.gguf

gguf · 3,38 GB · SHA-256 f0157b7914b7…bcac · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ3_XXS.gguf

gguf · 3,14 GB · SHA-256 34ab60cf3e59…e0b9 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ4_NL.gguf

gguf · 4,46 GB · SHA-256 8c213d233eeb…dcc7 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-IQ4_XS.gguf

gguf · 4,25 GB · SHA-256 366ed8516e13…a4b1 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q2_K_S.gguf

gguf · 2,87 GB · SHA-256 95dc9bafcfcf…95c8 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q2_K.gguf

gguf · 3,06 GB · SHA-256 301247064f59…7261 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q3_K_L.gguf

gguf · 4,13 GB · SHA-256 2b66e4df2013…1e1e · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q3_K_M.gguf

gguf · 3,84 GB · SHA-256 b0f0a9eb06d9…ff01 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q3_K_S.gguf

gguf · 3,51 GB · SHA-256 eb9d88254b5c…7b6c · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q4_0.gguf

gguf · 4,46 GB · SHA-256 2a1c3de8d8cb…b17b · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q4_1.gguf

gguf · 4,89 GB · SHA-256 9f80755a9ca3…7344 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q4_K_M.gguf

gguf · 4,68 GB · SHA-256 96f4ebf985bd…ca0f · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q4_K_S.gguf

gguf · 4,47 GB · SHA-256 babac55c4b98…b888 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q5_K_M.gguf

gguf · 5,45 GB · SHA-256 9027cd2a5979…ab90 · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q5_K_S.gguf

gguf · 5,33 GB · SHA-256 108dc2b56f3f…3dbc · Hugging Face

Download file

CoE-SlideVQA-8B.i1-Q6_K.gguf

gguf · 6,26 GB · SHA-256 be4e6c154c4b…c1d0 · Hugging Face

Download file

CoE-SlideVQA-8B.imatrix.gguf

gguf · 5,10 MB · SHA-256 00cc9b3cecc8…b7dc · Hugging Face

Download file

Extractos de fuentes

3 extractos
Readme2 agohuggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF

--- base_model: PeiyangLiu/CoE-SlideVQA-8B language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - multimodal - visual-question-answering - chain-of-evidence - slide-understanding - qwen3-vl --- ## 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/PeiyangLiu/CoE-SlideVQA-8B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CoE-SlideVQA-8B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/CoE-SlideVQA-8B-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/CoE-SlideVQA-8B-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/CoE-SlideVQA-8B-i1-GGUF/resolve/main/CoE-SlideVQA-8B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF/resolve/main/CoE-SlideVQA-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF/resolve/main/CoE-SlideVQA-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF/resolve/main/CoE-SlideVQA-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | | [GGUF](https://huggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF/resolve/main/CoE-SlideVQA-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | | [GGUF](https://huggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF/resolve/main/CoE-...

Note10 octhuggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF

Source context: 859 downloads · 0 likes · Pipeline visual-question-answering · Library transformers · Repo mradermacher/CoE-SlideVQA-8B-i1-GGUF

Note2 agohuggingface.co/mradermacher/CoE-SlideVQA-8B-i1-GGUF

Source context: 58 downloads · 0 likes · Pipeline visual-question-answering · Library transformers · Repo mradermacher/CoE-SlideVQA-8B-i1-GGUF