S

SmolVLM2-256M-Video-Instruct EU AI Act Compliance Profile

HuggingFaceTB

Image Text To Textapache-2.0transformers
① Risk Classification
LIMITED RISK
Art. 50, 52
Limited Risk AI System
② Model Info
256Mparameters
PipelineImage Text To Text
Librarytransformers
Licenseapache-2.0
Base ModelHuggingFaceTB/SmolVLM-256M-Instruct
Languagesen
SyncedApr 3, 2026
③ Popularity
156.7Kdownloads
98 likes
View on HuggingFace ↗
④ Obligations
2apply
~12h effort
□ AI Literacy (Art. 4)
□ AI Disclosure (Art. 50)
$ npx complior scan

Your risk depends on how you use SmolVLM2-256M-Video-Instruct

Usage ContextRisk LevelObligations
Internal coding toolMINIMAL3 obligations (~12h)
Customer support botLIMITED7 obligations (~32h)
HR screening / hiringHIGH19 obligations (~120h)
Credit decisionsHIGH19 obligations (~120h)
Medical triageHIGH19 obligations (~120h)

Why this tool is classified as LIMITED RISK

SmolVLM2-256M-Video-Instruct is a image text to text model by HuggingFaceTB. Fine-tuned from HuggingFaceTB/SmolVLM-256M-Instruct. Built with transformers. Supports en. Licensed under apache-2.0. 156.7K downloads on HuggingFace.

Applicable Articles

Art. 4AI Literacy (Art. 4)
REQUIREDDEADLINE PASSED
›
Obligation under Art. 4 for SmolVLM2-256M-Video-Instruct deployers.
Art. 50AI Disclosure (Art. 50)
REQUIREDDEADLINE PASSED
›

Who does what

HuggingFaceTB (provider)Their job

  • Provider obligations being compiled

You (deployer)Your job

  • •AI Literacy (Art. 4) (Art. 4)
  • •AI Disclosure (Art. 50) (Art. 50)
See full obligation checklist →

Risk Assessment Reasoning

The tool appears to be focused on image-text processing and video instruction, which may involve some risks related to content generation but does not pose significant threats to fundamental rights or safety. Its applications are likely to be controlled and used in a manner that mitigates risks.

More models by HuggingFaceTB

S
SmolLM2-135M
HuggingFaceTB
LIMITED RISK
1.1M DL135M
S
SmolLM3-3B
HuggingFaceTB
LIMITED RISK
1.1M DL3B
S
SmolLM2-135M-Instruct
HuggingFaceTB
LIMITED RISK
946.9K DL135M
S
SmolVLM-256M-Instruct
HuggingFaceTB
LIMITED RISK
312.7K DL256M

Similar Image Text To Text models

A
all-MiniLM-L6-v2
sentence-transformers
LIMITED RISK
200.4M DL
B
bert-base-uncased
google-bert
LIMITED RISK
71.4M DL
E
electra-base-discriminator
google
LIMITED RISK
49.3M DL
A
all-mpnet-base-v2
sentence-transformers
LIMITED RISK
28.9M DL
Browse all Image Text To Text models →

Frequently Asked Questions

What is SmolVLM2-256M-Video-Instruct's EU AI Act risk classification?

+

SmolVLM2-256M-Video-Instruct is classified as LIMITED RISK under the EU AI Act. The model has 256M parameters.

What are my obligations if I deploy SmolVLM2-256M-Video-Instruct?

+

As a SmolVLM2-256M-Video-Instruct deployer, you have 2 base obligations (~12 hours estimated effort). Key articles: Art. 4, Art. 50.

What is SmolVLM2-256M-Video-Instruct?

+

SmolVLM2-256M-Video-Instruct is a Image Text To Text model by HuggingFaceTB. It has 156.7K downloads on HuggingFace. Licensed under apache-2.0.

What are the EU AI Act deadlines for SmolVLM2-256M-Video-Instruct?

+

Already passed: AI Literacy (Art. 4) — 2025-02-02. Already passed: AI Disclosure (Art. 50) — 2025-08-02.

Check SmolVLM2-256M-Video-Instruct compliance in your codebase

One command to scan. Open-source CLI.

$ npx complior scan