Skip to main content

moondream

tiny vision language model

View on GitHub Official site
Vision Multimodal Apache-2.0 Medium setup 9,874 stars

Overview

Description

Moondream is a tiny but powerful vision language model that runs anywhere — from cloud servers to edge devices. It lets you add image understanding (captioning, visual Q&A, object detection) to your applications without massive infrastructure. The big picture: a 2B parameter model that punches above its weight, plus a 0.5B variant for resource-constrained hardware.

Technical scorecard

License

Apache-2.0

Commercial use

Yes

OpenAI-compatible API

No

REST API

No

Fine-tuning support

No

Quantization support

No

Docker available

No

GUI / no-code available

No

Telemetry

Unknown

Offline after setup

No

Data & Privacy

Does it send data online?

This listing is not marked offline after setup.

Does it store history?

Not verified in this directory yet. Review the upstream docs for persistence, logs, and workspace storage.

License checks?

Commercial use is marked as allowed or likely allowed by the listed license.

Telemetry?

Unknown

Last verified: Jul 22, 2026. Maintainer verification should be treated as directory guidance, not legal advice.

🛡️

Deploying moondream in production?

Stop silent telemetry leaks before they trigger an unintended data leak. Get our Airgap Certainty Blueprint for moondream.

Request Privacy and Telemetry Audit

Setup & Installation

Medium

A developer can usually get this running with standard docs.

# Start with the official project repository
# https://github.com/m87-labs/moondream

Hardware Requirements

Hardware tagsCPU, GPU (NVIDIA), GPU (Apple Silicon), Edge Device
LanguagesPython

Works Well With