Moondream 3.1 is a vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). It delivers state-of-the-art visual reasoning and detection while staying fast and cheap to deploy. Skills include query, detect, point, and caption, all native and all returning structured output.
For the full story on what's new — including how we trained it and how it holds up on your own tasks — see the release notes.
Photon is Moondream's high-performance inference engine. It runs the model locally on NVIDIA GPUs (Ampere or newer) and Apple Silicon Macs, with the same API as
Moondream Cloud.
1import moondream as md
2from PIL import Image
3
4# Runs locally via Photon. Weights download from Hugging Face on first use.
5model = md.vl(local=True, model="moondream3.1-9B-A2B")
6
7image = Image.open("photo.jpg")
8
9# Caption
10print(model.caption(image)["caption"])
11
12# Visual question answering
13print(model.query(image, "What's in this image?")["answer"])
14
15# Open-vocabulary detection
16for obj in model.detect(image, "person")["objects"]:
17 print(obj)
18
19# Pointing
20for point in model.point(image, "person")["points"]:
21 print(point)
No API key is required to run the base model locally. (You'll only need one to run finetunes or to call
Moondream Cloud.) For supported hardware, streaming, finetunes, and production serving with Triton, see the
local inference guide.
Prefer a hosted endpoint? The same skills are available through
Moondream Cloud with a generous free tier. See the
quickstart to make your first call.
Moondream 3.1 is released under the
Moondream Model License.
