# m87-labs/moondream

tiny vision language model

Repository: https://github.com/m87-labs/moondream
Canonical: https://ross.abutalabs.com/products/moondream
Homepage: https://moondream.ai
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-04-20T06:52:50+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 35, longevity 69
- inputs: {"age_days": 979, "days_push": 135, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10014, forks 793 (observed 2026-08-28T04:10:39.255859+00:00)

## What it is
Moondream is an open-weight family of small, efficient vision language models (2B to 9B MoE) that perform image captioning, visual question answering, object detection, pointing, counting, and segmentation. It ships with a Python package and the Photon local inference engine for NVIDIA GPUs and Apple Silicon, plus a hosted cloud API and fine-tuning service.

## Use cases
- caption images with a small local model
- run visual question answering on edge devices
- detect and locate objects in images with bounding boxes
- segment objects in images without heavy GPU hardware
- fine-tune a vision model on my own labeled images
- run a VLM on a Jetson or Apple Silicon Mac
- count objects in photos
- understand documents and charts with a vision model

## When to choose
- you need efficient image understanding on constrained hardware or at the edge
- you want open weights with commercial use allowed for local inference
- you need vision skills like detection, pointing, and segmentation out of the box
- you want low inference cost compared to frontier VLMs

## When to avoid
- you need frontier-level general reasoning or long-document understanding beyond its benchmarks
- you plan to host the model weights as a third-party cloud service, which the license restricts
- you need text-only LLM capabilities without vision

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, llm-inference, image-processing, sdk
- domain: computer-vision, artificial-intelligence, machine-learning, image-processing
- platform: python, windows, cloud, self-hosted
- tags: vision-language-model, vlm, image-captioning, visual-question-answering, object-detection, image-segmentation, edge-ai, mixture-of-experts, open-weights, fine-tuning, linux, macos, gpu

## Member repositories
- m87-labs/moondream (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:39.255859+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:20:00.047009+00:00, confidence not recorded.
  - readme: https://github.com/m87-labs/moondream (fetched 2026-08-28T04:10:39.255859+00:00, sha 5e1d10456992)
  - homepage: https://moondream.ai (fetched 2026-08-29T08:19:53.896197+00:00, sha 40b658a235ae)
  - site_page: https://docs.moondream.ai (fetched 2026-08-29T08:19:53.899169+00:00, sha 6451d1bc3c40)
  - site_page: https://docs.moondream.ai/running-locally (fetched 2026-08-29T08:19:53.905166+00:00, sha 5ee881489214)
  - site_page: https://moondream.ai/about/us (fetched 2026-08-29T08:19:53.907003+00:00, sha 6de36f8c26ce)
  - site_page: https://moondream.ai/about/careers (fetched 2026-08-29T08:19:53.908515+00:00, sha 70a46096af6a)
  - site_page: https://moondream.ai/pricing (fetched 2026-08-29T08:19:53.901169+00:00, sha 2a091caabffb)
  - site_page: https://moondream.ai/lens (fetched 2026-08-29T08:19:53.903064+00:00, sha cb94f1d05b31)
- Data as of 2026-08-30T08:39:29.467469+00:00.