SmolVLM2 2.2B Instruct GGUF
For a convenient overview and download list, visit our model page for this model.
Model source
- Kind
- Model
- File size
- 675 MB–3.38 GB
- Base model
- HuggingFaceTB/SmolVLM2-2.2B-Instruct
- Version
- vRevision 2bf3008
- Updated
- Oct 30, 2026
- Downloads
- 430
- Source
- Hugging Face
Source description
About
static quants of https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants are available at https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-GGUF
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)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | Q2_K | 0.8 | |
| GGUF | Q3_K_S | 0.9 | |
| GGUF | Q3_K_M | 1.0 | lower quality |
| GGUF | Q3_K_L | 1.1 | |
| GGUF | IQ4_XS | 1.1 | |
| GGUF | Q4_K_S | 1.2 | fast, recommended |
| GGUF | Q4_K_M | 1.2 | fast, recommended |
| GGUF | Q5_K_S | 1.4 | |
| GGUF | Q5_K_M | 1.4 | |
| GGUF | Q6_K | 1.6 | very good quality |
| GGUF | Q8_0 | 2.0 | fast, best quality |
| GGUF | f16 | 3.7 | 16 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
Sources
1 sourceVerified Oct 30
Download files
Repository files
File inventory only; completeness is unverified.
- SmolVLM2-2.2B-Instruct.IQ4_XS.gguf
- SmolVLM2-2.2B-Instruct.Q2_K.gguf
- SmolVLM2-2.2B-Instruct.Q3_K_L.gguf
- SmolVLM2-2.2B-Instruct.Q3_K_M.gguf
- SmolVLM2-2.2B-Instruct.Q3_K_S.gguf
- SmolVLM2-2.2B-Instruct.Q4_K_M.gguf
- SmolVLM2-2.2B-Instruct.Q4_K_S.gguf
- SmolVLM2-2.2B-Instruct.Q5_K_M.gguf
- SmolVLM2-2.2B-Instruct.Q5_K_S.gguf
- SmolVLM2-2.2B-Instruct.Q6_K.gguf
- SmolVLM2-2.2B-Instruct.Q8_0.gguf
- SmolVLM2-2.2B-Instruct.f16.gguf
Model artifacts
12 artifacts
Model artifacts
12 artifactsSmolVLM2-2.2B-Instruct.f16.gguf
gguf · 3.38 GB · SHA-256 7123d144b89e…37e8 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.IQ4_XS.gguf
gguf · 956 MB · SHA-256 0e9688465901…167e · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q2_K.gguf
gguf · Q2_K (unverified) · 675 MB · SHA-256 cb984933550e…8108 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q3_K_L.gguf
gguf · Q3_K_L (unverified) · 931 MB · SHA-256 1854a5759994…ae23 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q3_K_M.gguf
gguf · Q3_K_M (unverified) · 862 MB · SHA-256 5e95ab64967e…3ad1 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q3_K_S.gguf
gguf · Q3_K_S (unverified) · 782 MB · SHA-256 fb096c1500fd…d293 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q4_K_M.gguf
gguf · Q4_K_M (unverified) · 1.04 GB · SHA-256 0887067c02e0…89c7 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q4_K_S.gguf
gguf · Q4_K_S (unverified) · 1,007 MB · SHA-256 b1adf82d916c…a067 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q5_K_M.gguf
gguf · Q5_K_M (unverified) · 1.21 GB · SHA-256 cf9d7f3599f0…1a4b · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q5_K_S.gguf
gguf · Q5_K_S (unverified) · 1.18 GB · SHA-256 44381384e915…fc20 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q6_K.gguf
gguf · Q6_K (unverified) · 1.39 GB · SHA-256 53e413f9393e…7072 · Hugging Face
Download fileSmolVLM2-2.2B-Instruct.Q8_0.gguf
gguf · Q8_0 (unverified) · 1.80 GB · SHA-256 5a7180a083b8…5660 · Hugging Face
Download fileSource excerpts
3 excerpts
Source excerpts
3 excerpts--- 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: --> static 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-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-i1-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-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF/resolve/main/SmolVLM2-2.2B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/SmolVLM2-2.2B-...
Source context: 430 downloads · 4 likes · Pipeline video-text-to-text · Library transformers · Repo mradermacher/SmolVLM2-2.2B-Instruct-GGUF
Source context: 216 downloads · 4 likes · Pipeline video-text-to-text · Library transformers · Repo mradermacher/SmolVLM2-2.2B-Instruct-GGUF
