đ SmolVLM2-2.2B-Instruct Quantized Model
This project provides quantized versions of the SmolVLM2-2.2B-Instruct model, offering various options for different usage scenarios.
đ Quick Start
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.
⨠Features
- Multiple Datasets: Trained on a diverse set of datasets, including HuggingFaceM4/the_cauldron, HuggingFaceM4/Docmatix, and many others.
- Video-Text-to-Text: Capable of handling video and text input and generating text output.
- Quantized Versions: Available in various quantized formats for different performance and quality requirements.
đĻ Installation
No specific installation steps are provided in the original README.
đ Documentation
Model Information
| Property |
Details |
| Base Model |
HuggingFaceTB/SmolVLM2-2.2B-Instruct |
| Datasets |
HuggingFaceM4/the_cauldron, HuggingFaceM4/Docmatix, lmms-lab/LLaVA-OneVision-Data, etc. |
| Language |
en |
| Library Name |
transformers |
| License |
apache-2.0 |
| Quantized By |
mradermacher |
| Tags |
video-text-to-text |
About
Weighted/imatrix quants of https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct. Static quants are available at https://huggingface.co/mradermacher/SmolVLM2-2.2B-Instruct-GGUF.
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 |
i1-IQ1_S |
0.5 |
for the desperate |
| GGUF |
i1-IQ1_M |
0.6 |
mostly desperate |
| GGUF |
i1-IQ2_XXS |
0.6 |
|
| GGUF |
i1-IQ2_S |
0.7 |
|
| GGUF |
i1-IQ2_M |
0.8 |
|
| GGUF |
i1-Q2_K_S |
0.8 |
very low quality |
| GGUF |
i1-Q2_K |
0.8 |
IQ3_XXS probably better |
| GGUF |
i1-IQ3_XXS |
0.8 |
lower quality |
| GGUF |
i1-IQ3_XS |
0.9 |
|
| GGUF |
i1-IQ3_S |
0.9 |
beats Q3_K* |
| GGUF |
i1-Q3_K_S |
0.9 |
IQ3_XS probably better |
| GGUF |
i1-IQ3_M |
1.0 |
|
| GGUF |
i1-Q3_K_M |
1.0 |
IQ3_S probably better |
| GGUF |
i1-Q3_K_L |
1.1 |
IQ3_M probably better |
| GGUF |
i1-IQ4_XS |
1.1 |
|
| GGUF |
i1-IQ4_NL |
1.1 |
prefer IQ4_XS |
| GGUF |
i1-Q4_0 |
1.2 |
fast, low quality |
| GGUF |
i1-Q4_K_S |
1.2 |
optimal size/speed/quality |
| GGUF |
i1-Q4_K_M |
1.2 |
fast, recommended |
| GGUF |
i1-Q4_1 |
1.3 |
|
| GGUF |
i1-Q5_K_S |
1.4 |
|
| GGUF |
i1-Q5_K_M |
1.4 |
|
| GGUF |
i1-Q6_K |
1.6 |
practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
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.
đ License
This project is licensed under the apache-2.0 license.
đ 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.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)