Interfaze

logo

we're hiring

pricing

help

docs

blog

sign in

All models

SmolVLM2 256M Video Instruct

SmolVLM2 256M Video Instruct by HuggingFaceTB, a image-text-to-text model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities.

Comparison

FeatureSmolVLM2 256M Video InstructInterfaze
Input Modalities

text, image, video

image, text, audio, video, document

Native OCRNoYes
Long Document ProcessingNoYes
Language Support

unknown

162+

Native Speech-to-TextNoYes
Native Object DetectionNoYes
Guardrail ControlsNoYes
Context Input Size

unknown

1M

Tool CallingNo

Tool calling supported + built in browser, code execution and web search

Scaling

FeatureSmolVLM2 256M Video InstructInterfaze
Scaling

Self-hosted/Provider-hosted with quantization

Unlimited

Try InterfazeRead the Docs

View model card on Hugging Face

SmolVLM2-256M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.38GB of GPU RAM for video inference. This efficiency makes it particularly well-suited for on-device applications that require specific domain fine-tuning and computational resources may be limited.

Model Summary

  • Developed by: Hugging Face 🤗
  • Model type: Multi-modal model (image/multi-image/video/text)
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Architecture: Based on Idefics3 (see technical summary)

Resources

Uses

SmolVLM2 can be used for inference on multimodal (video / image / text) tasks where the input consists of text queries along with video or one or more images. Text and media files can be interleaved arbitrarily, enabling tasks like captioning, visual question answering, and storytelling based on visual content. The model does not support image or video generation.

To fine-tune SmolVLM2 on a specific task, you can follow the fine-tuning tutorial.

Evaluation

We evaluated the performance of the SmolVLM2 family on the following scientific benchmarks:

SizeVideo-MMEMLVUMVBench
2.2B52.155.246.27
500M42.247.339.73
256M33.740.632.7

How to get started

You can use transformers to load, infer and fine-tune SmolVLM. Make sure you have num2words, flash-attn and latest transformers installed. You can load the model as follows.

from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model_path = "HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
processor = AutoProcessor.from_pretrained(model_path)
model = AutoModelForImageTextToText.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    _attn_implementation="flash_attention_2"
).to("cuda")

Simple Inference

You preprocess your inputs directly using chat templates and directly passing them

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Can you describe this image?"},            
        ]
    },
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)
print(generated_texts[0])

Video Inference

To use SmolVLM2 for video inference, make sure you have decord installed.

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "path": "path_to_video.mp4"},
            {"type": "text", "text": "Describe this video in detail"}
        ]
    },
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)

print(generated_texts[0])

Multi-image Interleaved Inference

You can interleave multiple media with text using chat templates.

import torch


messages = [
    {
        "role": "user",
        "content": [
          {"type": "text", "text": "What is the similarity between these two images?"},
          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"},            
        ]
    },
]
inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
generated_texts = processor.batch_decode(
    generated_ids,
    skip_special_tokens=True,
)
print(generated_texts[0])

Model optimizations

Misuse and Out-of-scope Use

SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:

  • Prohibited Uses:
    • Evaluating or scoring individuals (e.g., in employment, education, credit)
    • Critical automated decision-making
    • Generating unreliable factual content
  • Malicious Activities:
    • Spam generation
    • Disinformation campaigns
    • Harassment or abuse
    • Unauthorized surveillance

License

SmolVLM2 is built upon SigLIP as image encoder and SmolLM2 for text decoder part.

We release the SmolVLM2 checkpoints under the Apache 2.0 license.

Citation information

You can cite us in the following way:

@article{marafioti2025smolvlm,
  title={SmolVLM: Redefining small and efficient multimodal models}, 
  author={Andrés Marafioti and Orr Zohar and Miquel Farré and Merve Noyan and Elie Bakouch and Pedro Cuenca and Cyril Zakka and Loubna Ben Allal and Anton Lozhkov and Nouamane Tazi and Vaibhav Srivastav and Joshua Lochner and Hugo Larcher and Mathieu Morlon and Lewis Tunstall and Leandro von Werra and Thomas Wolf},
  journal={arXiv preprint arXiv:2504.05299},
  year={2025}
}

Training Data

SmolVLM2 used 3.3M samples for training originally from ten different datasets: LlaVa Onevision, M4-Instruct, Mammoth, LlaVa Video 178K, FineVideo, VideoStar, VRipt, Vista-400K, MovieChat and ShareGPT4Video. In the following plots we give a general overview of the samples across modalities and the source of those samples.

Data Split per modality

Data TypePercentage
Image34.4%
Text20.2%
Video33.0%
Multi-image12.3%

Granular dataset slices per modality

Text Datasets

DatasetPercentage
llava-onevision/magpie_pro_ft3_80b_mt6.8%
llava-onevision/magpie_pro_ft3_80b_tt6.8%
llava-onevision/magpie_pro_qwen2_72b_tt5.8%
llava-onevision/mathqa0.9%

Multi-image Datasets

DatasetPercentage
m4-instruct-data/m4_instruct_multiimage10.4%
mammoth/multiimage-cap61.9%

Image Datasets

DatasetPercentage
llava-onevision/other17.4%
llava-onevision/vision_flan3.9%
llava-onevision/mavis_math_metagen2.6%
llava-onevision/mavis_math_rule_geo2.5%
llava-onevision/sharegpt4o1.7%
llava-onevision/sharegpt4v_coco1.5%
llava-onevision/image_textualization1.3%
llava-onevision/sharegpt4v_llava0.9%
llava-onevision/mapqa0.9%
llava-onevision/qa0.8%
llava-onevision/textocr0.8%

Video Datasets

DatasetPercentage
llava-video-178k/1-2m7.3%
llava-video-178k/2-3m7.0%
other-video/combined5.7%
llava-video-178k/hound4.4%
llava-video-178k/0-30s2.4%
video-star/starb2.2%
vista-400k/combined2.2%
vript/long1.0%
ShareGPT4Video/all0.8%

Want more deterministic results?

Interfaze

logo

Product

Playground

OCR

Models

Leaderboards

Pricing

OpenWebSearch

DefaultModel