Project AURIONAI Use-Cases Research & Innovation
Hugging Face
multimodal LLMfamily

SmolVLM

Small open vision language models (256M to 2.2B) for images and video that run on laptops and phones.

Pie chart of the SmolVLM training data mix by task type, from the model card.
Levelfamily
Classmultimodal LLM
Parametersnot in the notes
Contextnot in the notes
Released18 Nov 2024
Opennessopen weights permissive
Runs onlaptop, mobile or NPU
Statusactive

Lineage

Hugging FaceSmolVLM2 256M Video Instruct belongs to this familymultimodal LLM11 Feb 2025256.48M
Hugging FaceSmolVLM2 500M Video Instruct belongs to this familymultimodal LLM11 Feb 2025507.48M
Hugging FaceSmolVLM2 2.2B Instruct belongs to this familymultimodal LLM8 Feb 20252.25B
Hugging FaceSmolVLM Instruct belongs to this familymultimodal LLM18 Nov 20242.25B
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Identity

Developer
Hugging Face
Family
not in the notes
Released
18 Nov 2024 sourcesregistry date
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text, image, video
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
laptop, mobile or NPU
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
Model card languages: en
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. replicate.com/lucataco/smolvlm-instruct https://replicate.com/lucataco/smolvlm-instruct
  2. docs.roboflow.com/models/supported-models/smolvlm2.md https://docs.roboflow.com/models/supported-models/smolvlm2.md
  3. huggingface.co/HuggingFaceTB/SmolVLM-Instruct https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct
  4. huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SmolVLM", https://aurion.semai.id/models/hugging-face-smolvlm/, records of October 2026.