Aller au contenu
ModelPrésentéExterne
Browse files

SmolVLM2 2.2B Instruct I1 GGUF

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

Sourcehuggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF/tree/377b1a88a6a9946b07be2cf41c9e5574327aa6bf
TypeOtherModèle de baseHuggingFaceTB/SmolVLM2-2.2B-InstructVersionRevision 377b1a8BClasse

Source du modèle

Type
Other
Taille du fichier
425 MB–1,39 GB
Modèle de base
HuggingFaceTB/SmolVLM2-2.2B-Instruct
Version
vRevision 377b1a8
Mis à jour
24 oct. 2026
Téléchargements
692
Source
Hugging Face

Description de la source

About

weighted/imatrix quants of https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct

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

static quants are available at https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-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
GGUFi1-IQ1_S0.5for the desperate
GGUFi1-IQ1_M0.6mostly desperate
GGUFi1-IQ2_XXS0.6
GGUFi1-IQ2_XS0.7
GGUFi1-IQ2_S0.7
GGUFi1-IQ2_M0.8
GGUFi1-Q2_K_S0.8very low quality
GGUFi1-Q2_K0.8IQ3_XXS probably better
GGUFi1-IQ3_XXS0.8lower quality
GGUFi1-IQ3_XS0.9
GGUFi1-IQ3_S0.9beats Q3_K*
GGUFi1-Q3_K_S0.9IQ3_XS probably better
GGUFi1-IQ3_M1.0
GGUFi1-Q3_K_M1.0IQ3_S probably better
GGUFi1-Q3_K_L1.1IQ3_M probably better
GGUFi1-IQ4_XS1.1
GGUFi1-IQ4_NL1.1prefer IQ4_XS
GGUFi1-Q4_01.2fast, low quality
GGUFi1-Q4_K_S1.2optimal size/speed/quality
GGUFi1-Q4_K_M1.2fast, recommended
GGUFi1-Q4_11.3
GGUFi1-Q5_K_S1.4
GGUFi1-Q5_K_M1.4
GGUFi1-Q6_K1.6practically 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 377b1a88a6a9946b07be2cf41c9e5574327aa6bf
huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF/tree/377b1a88a6a9946b07be2cf41c9e5574327aa6bf

Vérifié 24 oct.

Download files

Artefacts du modèle

24 artefacts

SmolVLM2-2.2B-Instruct.i1-IQ1_M.gguf

gguf · 455 MB · SHA-256 009d602d8abb…fc83 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ1_S.gguf

gguf · 425 MB · SHA-256 04ef5aee2166…6d4f · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ2_M.gguf

gguf · 628 MB · SHA-256 3371d00775ec…7d1a · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ2_S.gguf

gguf · 587 MB · SHA-256 32e3064bf2cc…2c31 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ2_XS.gguf

gguf · 549 MB · SHA-256 c848291b5d49…af65 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ2_XXS.gguf

gguf · 506 MB · SHA-256 f5767c6b9dac…4e1d · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ3_M.gguf

gguf · 814 MB · SHA-256 719c767467f9…92ea · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ3_S.gguf

gguf · 782 MB · SHA-256 3565eac5fd5c…2e89 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ3_XS.gguf

gguf · 746 MB · SHA-256 a5767fdb564b…aac9 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ3_XXS.gguf

gguf · 690 MB · SHA-256 307e53636899…64e3 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ4_NL.gguf

gguf · 999 MB · SHA-256 c7a3920e5daf…5673 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-IQ4_XS.gguf

gguf · 948 MB · SHA-256 7b9f08362cea…b29f · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q2_K_S.gguf

gguf · 628 MB · SHA-256 6e37cf8be59d…478f · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q2_K.gguf

gguf · 675 MB · SHA-256 ef9d382a93d3…d895 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q3_K_L.gguf

gguf · 931 MB · SHA-256 537a4ad6dab7…4edd · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q3_K_M.gguf

gguf · 862 MB · SHA-256 38c1ec57e1cc…2fdc · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q3_K_S.gguf

gguf · 782 MB · SHA-256 c49e5177c77d…05e0 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q4_0.gguf

gguf · 1 002 MB · SHA-256 0794f9d23b3d…8b2a · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q4_1.gguf

gguf · 1,08 GB · SHA-256 268ebab5d75e…2dc1 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q4_K_M.gguf

gguf · 1,04 GB · SHA-256 ee7686d62803…1f62 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q4_K_S.gguf

gguf · 1 007 MB · SHA-256 0eb6069407a6…b10d · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q5_K_M.gguf

gguf · 1,21 GB · SHA-256 565c2b7f25c5…6286 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q5_K_S.gguf

gguf · 1,18 GB · SHA-256 c3a26390cb59…cf03 · Hugging Face

Download file

SmolVLM2-2.2B-Instruct.i1-Q6_K.gguf

gguf · 1,39 GB · SHA-256 660b1ae2ca77…7cd8 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme7 aoûthuggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF

--- base_model: HuggingFaceTB/SmolVLM2-2.2B-Instruct datasets: - HuggingFaceM4/the_cauldron - HuggingFaceM4/Docmatix - lmms-lab/LLaVA-OneVision-Data - lmms-lab/M4-Instruct-Data - HuggingFaceFV/finevideo - MAmmoTH-VL/MAmmoTH-VL-Instruct-12M - lmms-lab/LLaVA-Video-178K - orrzohar/Video-STaR - Mutonix/Vript - TIGER-Lab/VISTA-400K - Enxin/MovieChat-1K_train - ShareGPT4Video/ShareGPT4Video language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - video-text-to-text --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SmolVLM2-2.2B-Instruct-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-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/SmolVLM2-2.2B-Instruct-i1-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S...

Note24 oct.huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF

Source context: 692 downloads · 3 likes · Pipeline video-text-to-text · Library transformers · Repo mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF

Note7 aoûthuggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF

Source context: 326 downloads · 0 likes · Pipeline video-text-to-text · Library transformers · Repo mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF