moondream2

About

What moondream2 is

⚠️ This repository contains the latest version of Moondream 2, our previous generation model. The latest version of Moondream is Moondream 3 (Preview). Moondream is a small vision language model designed to run efficiently everywhere. Website / Demo / GitHub This repository contains the latest (2025-06-21) release of Moondream 2, as well as historical releases. The model is updated frequently, so we recommend specifying a revision as shown below if you're using it in a production application. Usage Changelog 2025-06-21 (full release notes) Grounded Reasoning Introduces a new step-by-step reasoning mode that explicitly grounds reasoning in spatial positions within the image before answering, leading to more precise visual interpretation (e.g., chart median calculations, accurate counting). Enable with reasoning=True in the query skill to trade off speed vs. accuracy. Sharper Object Detection Uses reinforcement learning on higher-quality bounding-box annotations to reduce object clumping and improve fine-grained detections (e.g., distinguishing “blue bottle” vs. “bottle”). Faster Text Generation Yields 20–40 % faster response generation via a new “superword” tokenizer and lightweight tokenizer transfer hypernetwork, which reduces the number of tokens emitted without loss in accuracy and eases future multilingual extensions. Improved UI Understanding Boosts ScreenSpot (UI element localization) performance from an F1\@0.5 of 60.3 to 80.4, making Moondream more effective for UI-focused applications. Reinforcement Learning Enhancements RL fine-tuning applied across 55 vision-language tasks to reinforce grounded reasoning and detection capabilities, with a roadmap to expand to \~120 tasks in the next update. 2025-04-15 (full release notes) 1. Improved chart understanding (ChartQA up from 74.8 to 77.5, 82.2 with PoT) 2. Added temperature and nucleus sampling to reduce repetitive outputs 3. Better OCR for documents and tables (prompt with “Transcribe the text” or “Transcribe the text in natural reading order”) 4. Object detection supports document layout detection (figure, formula, text, etc) 5. UI understanding (ScreenSpot F1\@0.5 up from 53.3 to 60.3) 6. Improved text

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys moondream2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (moondream2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"moondream2","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models