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

Libraries

How to use NyxKrage/moondream3-preview-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="NyxKrage/moondream3-preview-hf", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import Moondream3ForConditonalGeneration
model = Moondream3ForConditonalGeneration.from_pretrained("NyxKrage/moondream3-preview-hf", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NyxKrage/moondream3-preview-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NyxKrage/moondream3-preview-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NyxKrage/moondream3-preview-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

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

SGLang

How to use NyxKrage/moondream3-preview-hf 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 "NyxKrage/moondream3-preview-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NyxKrage/moondream3-preview-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "NyxKrage/moondream3-preview-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NyxKrage/moondream3-preview-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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

CalamitousFelicitousness commited on Dec 1, 2025

Commit

772c6e8

verified ·

1 Parent(s): 1101625

Turn off hardcoded debug

Browse files

It's probably not necessary to force debug output on, especially that it needs the dbg folder to be created ahead of time or it will cause a RuntimeError.

Files changed (1) hide show

modeling_moondream3.py +1 -1

modeling_moondream3.py CHANGED Viewed

@@ -45,7 +45,7 @@ _CONFIG_FOR_DOC = "Moondream3Config"
 import torch
-DEBUG=True
 def apply_rotary_pos_emb(
     q: torch.Tensor,  # [B, H, L, D]

 import torch
+DEBUG=False
 def apply_rotary_pos_emb(
     q: torch.Tensor,  # [B, H, L, D]