Instructions to use ewre324/moondream2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ewre324/moondream2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ewre324/moondream2",
	filename="moondream2-mmproj-f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ewre324/moondream2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ewre324/moondream2:F16
# Run inference directly in the terminal:
llama-cli -hf ewre324/moondream2:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ewre324/moondream2:F16
# Run inference directly in the terminal:
llama-cli -hf ewre324/moondream2:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ewre324/moondream2:F16
# Run inference directly in the terminal:
./llama-cli -hf ewre324/moondream2:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ewre324/moondream2:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ewre324/moondream2:F16

Use Docker

docker model run hf.co/ewre324/moondream2:F16

LM Studio
Jan

vLLM

How to use ewre324/moondream2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ewre324/moondream2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ewre324/moondream2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ewre324/moondream2:F16

Ollama
How to use ewre324/moondream2 with Ollama:
```
ollama run hf.co/ewre324/moondream2:F16
```

Unsloth Studio new

How to use ewre324/moondream2 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ewre324/moondream2 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ewre324/moondream2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ewre324/moondream2 to start chatting

Docker Model Runner
How to use ewre324/moondream2 with Docker Model Runner:
```
docker model run hf.co/ewre324/moondream2:F16
```

Lemonade

How to use ewre324/moondream2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ewre324/moondream2:F16

Run and chat with the model

lemonade run user.moondream2-F16

List all available models

lemonade list

Model for Gaze detection

/ Colab Demo / GitHub

Original Model card follows below:

Moondream is a small vision language model designed to run efficiently on edge devices.

Website / Demo / GitHub

This repository contains the latest (2025-01-09) release of Moondream, as well as historical releases. The model is updated frequently, so we recommend specifying a revision as shown below if you're using it in a production application.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image

model = AutoModelForCausalLM.from_pretrained(
    "vikhyatk/moondream2",
    revision="2025-01-09",
    trust_remote_code=True,
    # Uncomment to run on GPU.
    # device_map={"": "cuda"}
)

# Captioning
print("Short caption:")
print(model.caption(image, length="short")["caption"])

print("\nNormal caption:")
for t in model.caption(image, length="normal", stream=True)["caption"]:
    # Streaming generation example, supported for caption() and detect()
    print(t, end="", flush=True)
print(model.caption(image, length="normal"))

# Visual Querying
print("\nVisual query: 'How many people are in the image?'")
print(model.query(image, "How many people are in the image?")["answer"])

# Object Detection
print("\nObject detection: 'face'")
objects = model.detect(image, "face")["objects"]
print(f"Found {len(objects)} face(s)")

# Pointing
print("\nPointing: 'person'")
points = model.point(image, "person")["points"]
print(f"Found {len(points)} person(s)")

Downloads last month: 486

Safetensors

Model size

2B params

Tensor type

F16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support