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
```

CPU is forbidden ?

#24

by edmond - opened Oct 15, 2025

Discussion

edmond

Oct 15, 2025

No matter what I try to use cpu, I have :
Cell In[17], line 6
result = moondream.query(image=image, question="What's in this image?")

File ~/.cache/huggingface/modules/transformers_modules/moondream/moondream3-preview/e86382f00368618bfbbef8026cb606e9c0e3cd0e/moondream.py:635 in query
image = self.encode_image(image, settings)

File ~/.cache/huggingface/modules/transformers_modules/moondream/moondream3-preview/e86382f00368618bfbbef8026cb606e9c0e3cd0e/moondream.py:315 in encode_image
img_emb = self._run_vision_encoder(image)

File ~/.cache/huggingface/modules/transformers_modules/moondream/moondream3-preview/e86382f00368618bfbbef8026cb606e9c0e3cd0e/moondream.py:294 in _run_vision_encoder
return self._vis_proj(global_features, reconstructed)

File ~/.cache/huggingface/modules/transformers_modules/moondream/moondream3-preview/e86382f00368618bfbbef8026cb606e9c0e3cd0e/moondream.py:192 in _vis_proj
return vision_projection(g, r, self.vision, self.config.vision)

File ~/.cache/huggingface/modules/transformers_modules/moondream/moondream3-preview/e86382f00368618bfbbef8026cb606e9c0e3cd0e/vision.py:88 in vision_projection
final_features = torch.cat([global_features, reconstructed], dim=-1)

RuntimeError: torch.cat(): all input tensors must be on the same device. Received cpu and mps:0

err805

moondream org Nov 5, 2025

Currently MD3 only runs on CUDA as it uses Flex Attn, but we have a MLX implementation in the pipeline.

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