File 002 · Local Intelligence
Record 098 · Vision · 2024
24.98.IMoondream
vikhyat
“A tiny VLM you can run on a laptop CPU and still caption a photo.”
A vision model that fits in a USB stick's shadow.
Moondream made 'what is in this image?' a local, cheap call. HA, Immich, and scripts use it because it is small.
Opened tiny local vision-language.
Filed notes
- ~1–2B VLM
- CPU-friendly captioning
- Apache weights
SIC
7372
Prepackaged Software
NAICS
511210
Software Publishers
