Moondream 3 Preview
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
- Context window: 32K tokens
- Max output: 4K tokens
- Reads: text, image
- Writes: text