Aller au contenu
ModelPrésentéExterne
Browse files

Supertron VL 2B GGUF

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

Sourcehuggingface.co/mradermacher/Supertron-VL-2B-GGUF/tree/7c056bff83b1730bf08acf38c0ee98af9706c1ce
TypeOtherModèle de baseSurpem/Supertron-VL-2BVersionRevision 7c056bfBClasse

Source du modèle

Type
Other
Taille du fichier
424 MB–3,21 GB
Modèle de base
Surpem/Supertron-VL-2B
Version
vRevision 7c056bf
Mis à jour
10 oct. 2026
Téléchargements
227
Source
Hugging Face

Description de la source

About

static quants of https://huggingface.co/Surpem/Supertron-VL-2B

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

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

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
GGUFmmproj-Q8_00.5multi-modal supplement
GGUFQ2_K0.9
GGUFmmproj-f160.9multi-modal supplement
GGUFQ3_K_S1.0
GGUFQ3_K_M1.0lower quality
GGUFQ3_K_L1.1
GGUFIQ4_XS1.1
GGUFQ4_K_S1.2fast, recommended
GGUFQ4_K_M1.2fast, recommended
GGUFQ5_K_S1.3
GGUFQ5_K_M1.4
GGUFQ6_K1.5very good quality
GGUFQ8_01.9fast, best quality
GGUFf163.516 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.

Sources

1 source
Hugging FacePrincipalVersion 7c056bff83b1730bf08acf38c0ee98af9706c1ce
huggingface.co/mradermacher/Supertron-VL-2B-GGUF/tree/7c056bff83b1730bf08acf38c0ee98af9706c1ce

Vérifié 10 oct.

Download files

Artefacts du modèle

14 artefacts

Supertron-VL-2B.f16.gguf

gguf · 3,21 GB · SHA-256 db8b3339d275…3592 · Hugging Face

Download file

Supertron-VL-2B.IQ4_XS.gguf

gguf · 969 MB · SHA-256 09f6bbb4f25f…f832 · Hugging Face

Download file

Supertron-VL-2B.mmproj-f16.gguf

gguf · 781 MB · SHA-256 8e0f7129a662…51a5 · Hugging Face

Download file

Supertron-VL-2B.mmproj-Q8_0.gguf

gguf · 424 MB · SHA-256 c6ba205e693e…52ff · Hugging Face

Download file

Supertron-VL-2B.Q2_K.gguf

gguf · 742 MB · SHA-256 9c074c04301a…dd39 · Hugging Face

Download file

Supertron-VL-2B.Q3_K_L.gguf

gguf · 957 MB · SHA-256 41d8ec493295…7f6a · Hugging Face

Download file

Supertron-VL-2B.Q3_K_M.gguf

gguf · 896 MB · SHA-256 308faf201654…d714 · Hugging Face

Download file

Supertron-VL-2B.Q3_K_S.gguf

gguf · 827 MB · SHA-256 f55cd628712c…0e3c · Hugging Face

Download file

Supertron-VL-2B.Q4_K_M.gguf

gguf · 1,03 GB · SHA-256 cfc2f7916dd2…4fef · Hugging Face

Download file

Supertron-VL-2B.Q4_K_S.gguf

gguf · 1 011 MB · SHA-256 b0fd46e4cac5…3c05 · Hugging Face

Download file

Supertron-VL-2B.Q5_K_M.gguf

gguf · 1,17 GB · SHA-256 ec70ee00a4e9…4666 · Hugging Face

Download file

Supertron-VL-2B.Q5_K_S.gguf

gguf · 1,15 GB · SHA-256 07b68b2ec9ee…528b · Hugging Face

Download file

Supertron-VL-2B.Q6_K.gguf

gguf · 1,32 GB · SHA-256 347c0d444801…3844 · Hugging Face

Download file

Supertron-VL-2B.Q8_0.gguf

gguf · 1,71 GB · SHA-256 d3c244415de3…754e · Hugging Face

Download file

Extraits de sources

3 extraits
Readme1 aoûthuggingface.co/mradermacher/Supertron-VL-2B-GGUF

--- base_model: Surpem/Supertron-VL-2B language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - vision-language - chart-question-answering - visual-question-answering - multimodal - pytorch --- ## 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/Surpem/Supertron-VL-2B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Supertron-VL-2B-GGUF).*** weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## 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/Supertron-VL-2B-GGUF/resolve/main/Supertron-VL-2B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/Supertron-VL-2B-GGUF/resolve/main/Supertron-VL-2B.Q2_K.gguf) | Q2_K | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/Supertron-VL-2B-GGUF/resolve/main/Supertron-VL-2B.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/Supertron-VL-2B-GGUF/resolve/main/Supertron-VL-2B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | | [GGUF](https://huggingface.co/mradermacher/Supertron-VL-2B-GGUF/resolve/main/Supertron-VL-2B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Supertron-VL-2B-GGUF/resolve/main/Supertron-VL-2B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/Supertron-VL-2B-GGUF/resolve/main/Supertron-VL-2B.IQ4_XS.gguf) | IQ4_XS | 1....

Note10 oct.huggingface.co/mradermacher/Supertron-VL-2B-GGUF

Source context: 227 downloads · 0 likes · Pipeline visual-question-answering · Library transformers · Repo mradermacher/Supertron-VL-2B-GGUF

Note1 aoûthuggingface.co/mradermacher/Supertron-VL-2B-GGUF

Source context: 184 downloads · 0 likes · Pipeline visual-question-answering · Library transformers · Repo mradermacher/Supertron-VL-2B-GGUF