An open-source visual language model that interprets images via text prompts, fast and powerful.
7.7K
Moondream is an open-source visual language model that understands images using simple text prompts. It's fast and wildly capable.
| Attribute | Details |
|---|---|
| Provider | moondream.ai |
| Architecture | phi2 |
| 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/moondream2:1.5Bai/moondream2:1.5B-F16ai/moondream2:latest | 1.42 B | MOSTLY_F16 | 2K tokens | 3.72 GiB | 2.64 GB |
¹: VRAM estimated based on model characteristics.
latest→1.5B
docker model run ai/moondream2
Content type
Model
Digest
sha256:2b17b4e27…
Size
3.5 GB
Last updated
8 months ago
docker model pull ai/moondream2:1.5BPulls:
30
Jun 1 to Jun 7