Categories
Blog
Model Release
March 10, 2026Moondream Segmenting Update: Better Masks, Better Benchmarks, 40% Faster
Moondream Cloud segmenting now delivers stronger benchmark scores, improved mask quality, and 40% faster inference.
Read more
Announcement
December 19, 2025We added Moondream 3 Preview support to Moondream Station
Mac users can now run Moondream 3 Preview in Station with MLX-native, quantized performance.
Read more
Announcement
October 17, 2025Announcing Moondream Cloud
Fast, cheap, smart. Pick three.
Read more
Release
September 23, 2025Moondream Station 2: Simpler, more features, and Windows!
Moondream Station 2 is a one-line installer to run Moondream locally
Read more
Model Release
September 18, 2025Moondream 3 Preview: Frontier-level reasoning at a blazing speed
Think deeper, detect smarter, run just as fast.
Read more
Model Release
June 23, 2025Moondream Update: Grounded Reasoning, Better Detection, Faster Generation
Think deeper, detect smarter, run faster.
Read more
Announcement
May 21, 2025Fewer bits, more dreams
Moondream now supports 4-bit quantization, making it faster and smaller.
Read more
Announcement
May 1, 2025Moondream Station Launch
Moondream Station is a one-click solution to running Moondream locally.
Read more
Model Release
April 14, 2025Top Left: 2025-04-14 Release
Moondream is not just one of the tiniest VLMs. It's the world' most efficient VLM with improved document understanding and counting ability.
Read more