SmolVLM
Model FamilyHugging Faceactive
Family of compact open vision-language models designed for efficient multimodal inference on constrained devices.
- Nov 28, 2024
- —
- textimagevideo
- Yes
- —
- 0
Models in this family
| Model | Family | Released | Modality | Open source | API | Status |
|---|---|---|---|---|---|---|
| SmolVLM2 | SmolVLM | Feb 20, 2025 | textimagevideo | Yes | — | active |
| SmolVLM 256M | SmolVLM | Jan 23, 2025 | textimage | Yes | — | active |
| SmolVLM 500M | SmolVLM | Jan 23, 2025 | textimage | Yes | — | active |
| SmolVLM 2B | SmolVLM | Nov 28, 2024 | textimage | Yes | — | active |
Releases
No releases recorded for this entry.