Aller au contenu
ModelVérifiéExterne
Télécharger

EAR Qwen2.5 VL 3B I1 GGUF

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

Sourcehuggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF/tree/b21873076ac8638d7964ce8303b001ca409228b6
TypeOtherModèle de baseAlleyOop26/EAR-Qwen2.5-VL-3BVersionRevision b218730Éditeur@mradermacherCClasse

Source du modèle

Type
Other
Taille du fichier
3,24 MB–2,36 GB
Modèle de base
AlleyOop26/EAR-Qwen2.5-VL-3B
Version
vRevision b218730
Mis à jour
3 oct. 2026
Éditeur
@mradermacher
Téléchargements
604
Paramètres
3B
Source
Hugging Face

Description de la source

About

weighted/imatrix quants of https://huggingface.co/AlleyOop26/EAR-Qwen2.5-VL-3B

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

static quants are available at https://huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-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_S0.9for the desperate
GGUFi1-IQ1_M1.0mostly desperate
GGUFi1-IQ2_XXS1.0
GGUFi1-IQ2_XS1.1
GGUFi1-IQ2_S1.2
GGUFi1-IQ2_M1.2
GGUFi1-Q2_K_S1.3very low quality
GGUFi1-Q2_K1.4IQ3_XXS probably better
GGUFi1-IQ3_XXS1.4lower quality
GGUFi1-IQ3_XS1.5
GGUFi1-Q3_K_S1.6IQ3_XS probably better
GGUFi1-IQ3_S1.6beats Q3_K*
GGUFi1-IQ3_M1.6
GGUFi1-Q3_K_M1.7IQ3_S probably better
GGUFi1-Q3_K_L1.8IQ3_M probably better
GGUFi1-IQ4_XS1.8
GGUFi1-IQ4_NL1.9prefer IQ4_XS
GGUFi1-Q4_01.9fast, low quality
GGUFi1-Q4_K_S1.9optimal size/speed/quality
GGUFi1-Q4_K_M2.0fast, recommended
GGUFi1-Q4_12.1
GGUFi1-Q5_K_S2.3
GGUFi1-Q5_K_M2.3
GGUFi1-Q6_K2.6practically 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.

Sources

1 source
Hugging FacePrincipalVersion b21873076ac8638d7964ce8303b001ca409228b6
huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF/tree/b21873076ac8638d7964ce8303b001ca409228b6

Vérifié 3 oct.

Artefacts du modèle

25 artefacts

EAR-Qwen2.5-VL-3B.i1-IQ1_M.gguf

gguf · 811 MB · SHA-256 0da7f033abe2…5b63 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ1_S.gguf

gguf · 754 MB · SHA-256 8cb4216f117e…5f0b · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ2_M.gguf

gguf · 1,06 GB · SHA-256 41996b6e9499…508e · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ2_S.gguf

gguf · 1 013 MB · SHA-256 1abc42827c75…b238 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ2_XS.gguf

gguf · 984 MB · SHA-256 b2b19d769977…8892 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ2_XXS.gguf

gguf · 904 MB · SHA-256 326dd092fa6f…be5c · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ3_M.gguf

gguf · 1,39 GB · SHA-256 7944adcc5e97…a00c · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ3_S.gguf

gguf · 1,36 GB · SHA-256 98de6c2b595b…dec0 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ3_XS.gguf

gguf · 1,30 GB · SHA-256 cc5d6036dcee…1a12 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ3_XXS.gguf

gguf · 1,19 GB · SHA-256 589327697039…74a8 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ4_NL.gguf

gguf · 1,70 GB · SHA-256 bb9eb34d3466…dad8 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-IQ4_XS.gguf

gguf · 1,62 GB · SHA-256 34ae9db33d4b…d50a · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q2_K_S.gguf

gguf · 1,12 GB · SHA-256 89c9cc8952a1…aab0 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q2_K.gguf

gguf · 1,19 GB · SHA-256 0d681d4668d7…4ad3 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q3_K_L.gguf

gguf · 1,59 GB · SHA-256 96be5dd8409b…ce55 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q3_K_M.gguf

gguf · 1,48 GB · SHA-256 3910ce75a10e…7c62 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q3_K_S.gguf

gguf · 1,35 GB · SHA-256 ced59095fd61…954c · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q4_0.gguf

gguf · 1,70 GB · SHA-256 0f986b4b3624…5e04 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q4_1.gguf

gguf · 1,86 GB · SHA-256 d206fa2e8e67…a670 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q4_K_M.gguf

gguf · 1,80 GB · SHA-256 be8b38bdb046…4094 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q4_K_S.gguf

gguf · 1,71 GB · SHA-256 c9ceabfca2a9…f0dc · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q5_K_M.gguf

gguf · 2,07 GB · SHA-256 2154ee14720f…9ced · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q5_K_S.gguf

gguf · 2,02 GB · SHA-256 794bcfa7205d…5ce5 · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.i1-Q6_K.gguf

gguf · 2,36 GB · SHA-256 1e10d509f4f9…33ea · Hugging Face

Télécharger

EAR-Qwen2.5-VL-3B.imatrix.gguf

gguf · 3,24 MB · SHA-256 ea26b7b3544c…70b8 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme11 juil.huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF

--- base_model: AlleyOop26/EAR-Qwen2.5-VL-3B language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## 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/AlleyOop26/EAR-Qwen2.5-VL-3B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#EAR-Qwen2.5-VL-3B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-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/EAR-Qwen2.5-VL-3B-i1-GGUF/resolve/main/EAR-Qwen2.5-VL-3B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF/resolve/main/EAR-Qwen2.5-VL-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF/resolve/main/EAR-Qwen2.5-VL-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF/resolve/main/EAR-Qwen2.5-VL-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | | [GGUF](https://huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF/resolve/main/EAR-Qwen2.5-VL-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF/resolve/main/EAR-Qwen2.5-VL-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | | [GGUF](https://h...

Note3 oct.huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF

Source context: 604 downloads · 1 likes · Library transformers · Repo mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF

Note17 juil.huggingface.co/mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF

Source context: 240 downloads · 1 likes · Library transformers · Repo mradermacher/EAR-Qwen2.5-VL-3B-i1-GGUF