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
```

vikhyatk commited on Sep 17, 2025

Commit

d010875

verified ·

1 Parent(s): 05d8a39

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ Architecture details:
 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](https://huggingface.co/moondream/starmie-v1)
 4. Multi-headed attention with learned position- and data-dependent temperature scaling
-5. Vision encoder initialized from SigLIP-SO-400M, with multi-crop channel concatenation for token-efficient high resolution image processing
 For more details, please refer to our ||coming soon release blog post||. Or try the model out in our [playground demo](https://moondream.ai/c/playground).

 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](https://huggingface.co/moondream/starmie-v1)
 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 our ||coming soon release blog post||. Or try the model out in our [playground demo](https://moondream.ai/c/playground).