Instructions to use moondream/moondream3-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moondream/moondream3-preview with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="moondream/moondream3-preview", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("moondream/moondream3-preview", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use moondream/moondream3-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moondream/moondream3-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moondream/moondream3-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/moondream/moondream3-preview

SGLang

How to use moondream/moondream3-preview with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "moondream/moondream3-preview" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moondream/moondream3-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "moondream/moondream3-preview" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moondream/moondream3-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use moondream/moondream3-preview with Docker Model Runner:
```
docker model run hf.co/moondream/moondream3-preview
```

What are the metrics/eval framework?

#20

by wamreyaz - opened Oct 6, 2025

Discussion

wamreyaz

Oct 6, 2025

Hey,

Congrats on the amazing release.

I had a question about the evals

What are the metrics you actually report in this table? Particularly the Referring Expressions, is it accuracy as implemented in lmms-eval? If yes, what threshold?

If not, are you using mAP, which should be the standard for Object Detection?

Looking forward to your reply!

err805

moondream org Oct 6, 2025

•

edited Oct 6, 2025

Thanks!

For the referral benchmarks, we use the standard accuracy @ 50% IoU. For the rest, we follow the implementation in VLMEvalKit (https://github.com/open-compass/VLMEvalKit).

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment