Ir para o conteúdo
ModelVerificadoExterno
Baixar

Vision DeepResearch 30B A3B GGUF

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

Fontehuggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF/tree/2cb4adea37a3b14b04e9f8da183dc9966041dcf4
TipoOtherModelo baseOsilly/Vision-DeepResearch-30B-A3BVersãoRevision 2cb4adePublicador@mradermacherCnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
679 MB–30,3 GB
Modelo base
Osilly/Vision-DeepResearch-30B-A3B
Versão
vRevision 2cb4ade
Atualizado
3 de out. de 2026
Publicador
@mradermacher
Downloads
185
Parâmetros
30B
Fonte
Hugging Face

Descrição da fonte

About

static quants of https://huggingface.co/Osilly/Vision-DeepResearch-30B-A3B

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_00.8multi-modal supplement
GGUFmmproj-f161.2multi-modal supplement
GGUFQ2_K11.4
GGUFQ3_K_S13.4
GGUFQ3_K_M14.8lower quality
GGUFQ3_K_L16.0
GGUFIQ4_XS16.7
GGUFQ4_K_S17.6fast, recommended
GGUFQ4_K_M18.7fast, recommended
GGUFQ5_K_S21.2
GGUFQ5_K_M21.8
GGUFQ6_K25.2very good quality
GGUFQ8_032.6fast, best quality

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.

Fontes

1 fonte
Hugging FacePrimárioVersão 2cb4adea37a3b14b04e9f8da183dc9966041dcf4
huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF/tree/2cb4adea37a3b14b04e9f8da183dc9966041dcf4

Verificado 3 de out.

Artefatos de modelo

13 artefatos

Vision-DeepResearch-30B-A3B.IQ4_XS.gguf

gguf · 15,4 GB · SHA-256 6ad6db5375dc…9f21 · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.mmproj-f16.gguf

gguf · 1,01 GB · SHA-256 66dbed6264ef…aa7d · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.mmproj-Q8_0.gguf

gguf · 679 MB · SHA-256 cdfde7061d46…047d · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q2_K.gguf

gguf · 10,5 GB · SHA-256 5a1d7c364bbb…ff17 · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q3_K_L.gguf

gguf · 14,8 GB · SHA-256 89b1ba65b1c2…ef86 · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q3_K_M.gguf

gguf · 13,7 GB · SHA-256 af58e29dd1a5…6874 · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q3_K_S.gguf

gguf · 12,4 GB · SHA-256 c6ba4993d0b2…3cfe · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q4_K_M.gguf

gguf · 17,3 GB · SHA-256 aafc68441136…b70d · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q4_K_S.gguf

gguf · 16,3 GB · SHA-256 ae2b14ba6f35…ee88 · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q5_K_M.gguf

gguf · 20,2 GB · SHA-256 a1d86018011b…9ea8 · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q5_K_S.gguf

gguf · 19,6 GB · SHA-256 a2b3127227c9…0377 · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q6_K.gguf

gguf · 23,4 GB · SHA-256 3506ba4ec89c…0db5 · Hugging Face

Baixar

Vision-DeepResearch-30B-A3B.Q8_0.gguf

gguf · 30,3 GB · SHA-256 f3aea951735c…a5e6 · Hugging Face

Baixar

Trechos de fonte

3 trechos
Readme11 de jul.huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF

--- base_model: Osilly/Vision-DeepResearch-30B-A3B language: - en library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## 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/Osilly/Vision-DeepResearch-30B-A3B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Vision-DeepResearch-30B-A3B-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/Vision-DeepResearch-30B-A3B-GGUF/resolve/main/Vision-DeepResearch-30B-A3B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.8 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF/resolve/main/Vision-DeepResearch-30B-A3B.mmproj-f16.gguf) | mmproj-f16 | 1.2 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF/resolve/main/Vision-DeepResearch-30B-A3B.Q2_K.gguf) | Q2_K | 11.4 | | | [GGUF](https://huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF/resolve/main/Vision-DeepResearch-30B-A3B.Q3_K_S.gguf) | Q3_K_S | 13.4 | | | [GGUF](https://huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF/resolve/main/Vision-DeepResearch-30B-A3B.Q3_K_M.gguf) | Q3_K_M | 14.8 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF/resolve/main/Vision-DeepResearch-30B-A3B.Q3_K_L.gguf) | Q3_K_L | 16.0 | | | [GGUF](https://huggingface.co/mradermacher/V...

Note17 de jul.huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF

Source context: 90 downloads · 0 likes · Library transformers · Repo mradermacher/Vision-DeepResearch-30B-A3B-GGUF

Note11 de jul.huggingface.co/mradermacher/Vision-DeepResearch-30B-A3B-GGUF

Source context: 185 downloads · 0 likes · Library transformers · Repo mradermacher/Vision-DeepResearch-30B-A3B-GGUF