SmolVLM: lightweight multimodal model for video, image, and text analysis, optimized for devices.
10K+
SmolVLM 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 1.8GB of GPU RAM for video inference, it delivers robust performance on complex multimodal tasks. This efficiency makes it particularly well-suited for on-device applications where computational resources may be limited.
| Attribute | Details |
|---|---|
| Provider | Hugging Face |
| Architecture | Llama |
| Cutoff date | - |
| Languages | English |
| Tool calling | ❌ |
| Input modalities | Text, Image |
| Output modalities | Text |
| License | Apache 2.0 |
| Model variant | Parameters | Quantization | Context window | VRAM¹ | Size |
|---|---|---|---|---|---|
ai/smolvlm:500Mai/smolvlm:500M-F16ai/smolvlm:latest | 500M | MOSTLY_F16 | 8K tokens | 1.15 GiB | 780.71 MB |
ai/smolvlm:500M-Q8_0 | 500M | MOSTLY_Q8_0 | 8K tokens | 0.84 GiB | 414.86 MB |
¹: VRAM estimated based on model characteristics.
latest→500M
docker model run ai/smolvlm
Content type
Model
Digest
sha256:0cae12900…
Size
972.7 MB
Last updated
7 months ago
docker model pull ai/smolvlm:500MPulls:
176
Last week