moondream

VLMs too slow for production? Not anymore: 46ms end-to-end inference, 60+ fps on a single H100. Introducing Photon, Moondream's inference engine. Runs on everything from edge to server. moondream.ai/blog/photon-re…

Full tutorial: youtube.com/watch?v=MvdYSf…

How to fine-tune Moondream to detect the player holding the basketball. Full walkthrough.

Even more details: moondream.ai/blog/photon-1-…

Bottom line: Photon 1.2.0 makes Moondream faster, easier to deploy, and available on more of the hardware you use. Production vision AI is moving from “cloud-only” to “run it where the work happens.”

Photon 1.2.0 is here 🚀 ✅ Apple Silicon support ✅ Native Windows CUDA inference ✅ NVIDIA Blackwell support ✅ Jetson Thor edge inference ✅ Faster existing NVIDIA GPU performance Learn more👇

Base Moondream: 18 percent accuracy on glaucoma detection. GPT-5.4: 33 percent. Moondream plus Lens: 69 percent. Got a Vision AI challenge? Let us show you what Lens can do.

Powering the only agentic vision demo at NAB! Moondream counts people over time, captions the scene, and detects the thumbs up people are giving @ptzoptics.

Launching Lens, our fine-tuning service for Moondream. Improve Moondream's accuray to production-ready levels in hours, with as few as 20 images. Example: we taught Moondream to find the player with the ball in NBA footage. F1 jumped from 28% to 79%, beating ChatGPT. 54 minutes, $16.89. Fine-tune your own: moondream.ai/blog/lens-moon…

Cameras that follow the ball are over. PTZOptics + Moondream demo at NAB 2026 today: AI that understands who has the ball, when a shot happens, what the play is. Not tracking. Context. Every sports broadcast truck runs a vision-language model in 5 years.

Technical whitepaper on Moondream segmentation is out: arxiv.org/abs/2604.02593

@simonw @bechhof Yes, will launch Mac support this weekend.

@moondreamai @bechhof "Runs on everything from edge to server" - does everything include Macs?

VLMs too slow for production? Not anymore: 46ms end-to-end inference, 60+ fps on a single H100. Introducing Photon, Moondream's inference engine. Runs on everything from edge to server. moondream.ai/blog/photon-re…

@klyap_ Gotta keep our coding agent overlords happy.

@moondreamai the api design is CLEAN 👌🔥

@xeophon Yep.

@moondreamai is Photon Kestral?

Prompt. Point. Detect. Segment. One model, four ways to find anything in an image.

Moondream segmentation just leveled up. ↑ Better masks ↑ New SOTA benchmarks ↑ 40% faster Already live on Moondream Cloud. Local model + technical whitepaper coming later this week. Read more: moondream.ai/blog/segmentin…

5M downloads last month. LFG ☾!