moondream3

Moondream 3 (Preview) is an vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). This model makes no compromises, delivering state-of-the-art visual reasoning while still retaining our efficient and deployment-friendly ethos.

✨ Demo   ·   ☁️ Cloud API   ·   📝 Release notes

Architecture

1. 24 layers; the first four are dense, the rest have MoE FFNs with 64 experts, 8 activated per token
2. MoE FFNs have GeGLU architecture, with inner/gate dim of 1024. The model's hidden dim is 2048.
3. Usable context length increased to 32K, with a custom efficient SuperBPE tokenizer
4. Multi-headed attention with learned position- and data-dependent temperature scaling
5. SigLIP-based vision encoder, with multi-crop channel concatenation for token-efficient high resolution image processing

For more details, please refer to the [release notes]((https://moondream.ai/blog/moondream-3-preview). Or try the model out in our playground demo.

The following instructions demonstrate how to run the model locally using Transformers. We also offer a cloud API with a generous free tier that can help you get started quicker!

Usage

Load the model and prepare it for inference. We use FlexAttention for inference, so calling .compile() is critical for fast decoding. Our compile implementation also handles warmup, so you can start making requests directly once it returns.

import torch
from transformers import AutoModelForCausalLM

moondream = AutoModelForCausalLM.from_pretrained(
    "moondream/moondream3-preview",
    trust_remote_code=True,
    dtype=torch.bfloat16,
    device_map={"": "cuda"},
)
moondream.compile()

The model comes with four skills, tailored towards different visual understanding tasks.

Query

The query skill can be used to ask open-ended questions about images.

from PIL import Image

# Simple VQA
image = Image.open("photo.jpg")
result = moondream.query(image=image, question="What's in this image?")
print(result["answer"])

By default, query runs in reasoning mode, allowing the model to "think" about the question before generating an answer. This is helpful for more complicated tasks, but sometimes the task you're running is simple and doesn't benefit from reasoning. To save on inference cost when this is the case, you can disable reasoning:

# Without reasoning for simple questions
result = moondream.query(
    image=image,
    question="What color is the sky?",
    reasoning=False
)
print(result["answer"])

If you want to stream outputs, pass in stream=True. You can control the temperature, top-p, and maximum number of tokens generated by passing in optional settings.

# Streaming with custom settings
settings = {
    "temperature": 0.7,
    "top_p": 0.95,
    "max_tokens": 512
}

result = moondream.query(
    image=image,
    question="Describe what's happening in detail",
    stream=True,
    settings=settings
)

# Stream the answer
for chunk in result["answer"]:
    print(chunk, end="", flush=True)

Note that this isn't just for images; Moondream is also a strong general-purpose text model.

# Text-only example (no image)
result = moondream.query(
    question="Explain the concept of machine learning in simple terms"
)
print(result["answer"])

Caption

Whether you want short, normal-sized or long descriptions of images, the caption skill has you covered.

# Different caption lengths
image = Image.open("landscape.jpg")

# Short caption
short = moondream.caption(image, length="short")
print(f"Short: {short['caption']}")

# Normal caption (default)
normal = moondream.caption(image, length="normal")
print(f"Normal: {normal['caption']}")

# Long caption
long = moondream.caption(image, length="long")
print(f"Long: {long['caption']}")

It accepts the same streaming and temperature etc. settings as the query skill.

# Streaming caption with custom settings
result = moondream.caption(
    image,
    length="long",
    stream=True,
    settings={"temperature": 0.3}
)

for chunk in result["caption"]:
    print(chunk, end="", flush=True)

Point

The point skill identifies specific points (x, y coordinates) for objects in an image.

# Find points for specific objects
image = Image.open("crowd.jpg")
result = moondream.point(image, "person wearing a red shirt")

# Points are normalized coordinates (0-1)
for i, point in enumerate(result["points"]):
    print(f"Point {i+1}: x={point['x']:.3f}, y={point['y']:.3f}")

Detect

The detect skill provides bounding boxes for objects in an image.

# Detect objects with bounding boxes
image = Image.open("street_scene.jpg")
result = moondream.detect(image, "car")

# Bounding boxes are normalized coordinates (0-1)
for i, obj in enumerate(result["objects"]):
    print(f"Object {i+1}: "
          f"x_min={obj['x_min']:.3f}, y_min={obj['y_min']:.3f}, "
          f"x_max={obj['x_max']:.3f}, y_max={obj['y_max']:.3f}")

# Control maximum number of objects
settings = {"max_objects": 10}
result = moondream.detect(image, "person", settings=settings)

Caching image encodings (advanced)

If you're planning to run multiple inferences on the same image, you can pre-encode it once and reuse the encoding for better performance.

# Encode image once
image = Image.open("complex_scene.jpg")
encoded = moondream.encode_image(image)

# Reuse the encoding for multiple queries
questions = [
    "How many people are in this image?",
    "What time of day was this taken?",
    "What's the weather like?"
]

for q in questions:
    result = moo