Image + text

Moondream

A small, fast vision model for product use cases: answering questions, finding and pointing to objects, captions. Moondream 3.1 is a 9B MoE with 2B active.

Developer
Moondream (M87 Labs), USA
First release
Jan 2024
Latest release
Jun 2026
Sizes
2B – 9B-A2B
License
Commercial use with conditionsMoondream 2: Apache 2.0; Moondream 3: Moondream Model License (commercial use in your own products is allowed; you cannot sell access to the model itself as a cloud service)
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Manufacturing and logistics, Retail and marketplaces, Security
Deploy on your server Hugging Face GitHub

What it does

  • Finding and counting objects in photos
  • Checking photos from field reports
  • Captions and tags for a catalogue
  • Processing camera frames

Where it is used

Retail and warehousingField servicesE-commerce

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Moondream 3.1 9B-A2B
  2. Moondream 3 Preview
  3. moondream2
  4. moondream1

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Moondream be used in a commercial project?

With conditions. License: Moondream 2: Apache 2.0; Moondream 3: Moondream Model License (commercial use in your own products is allowed; you cannot sell access to the model itself as a cloud service). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Moondream need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Moondream support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Moondream and what does it cost?

The Moondream weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Image + textFlorence-2Microsoft · USACommercial use allowed

A very small vision model: captions, object detection, segmentation and text reading from a single prompt. Runs even on a CPU.

DetailsImage + textSmolVLMHugging Face · France / USACommercial use allowed

The smallest vision models from Hugging Face, starting at 256M; they run in a browser and on a phone. SmolVLM2 also understands video.

DetailsImage + textMolmoAi2 (Allen Institute for AI) · USACommercial use allowed

Fully open vision models from Ai2 (weights and data). They can point to a spot in an image and count objects; Molmo2 understands video, MolmoWeb controls a browser.

Details

Source: huggingface.co/moondream/moondream3.1-9B-A2B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.