Instructions to use cksghl1004/cpp_moondream2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cksghl1004/cpp_moondream2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cksghl1004/cpp_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 Settings

llama.cpp

How to use cksghl1004/cpp_moondream2 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cksghl1004/cpp_moondream2:F16
# Run inference directly in the terminal:
llama cli -hf cksghl1004/cpp_moondream2:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cksghl1004/cpp_moondream2:F16
# Run inference directly in the terminal:
llama cli -hf cksghl1004/cpp_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 cksghl1004/cpp_moondream2:F16
# Run inference directly in the terminal:
./llama-cli -hf cksghl1004/cpp_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 cksghl1004/cpp_moondream2:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cksghl1004/cpp_moondream2:F16

Use Docker

docker model run hf.co/cksghl1004/cpp_moondream2:F16

LM Studio
Jan

vLLM

How to use cksghl1004/cpp_moondream2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cksghl1004/cpp_moondream2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cksghl1004/cpp_moondream2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cksghl1004/cpp_moondream2:F16

Ollama
How to use cksghl1004/cpp_moondream2 with Ollama:
```
ollama run hf.co/cksghl1004/cpp_moondream2:F16
```

Unsloth Studio

How to use cksghl1004/cpp_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 cksghl1004/cpp_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 cksghl1004/cpp_moondream2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cksghl1004/cpp_moondream2 to start chatting

Atomic Chat new
Docker Model Runner
How to use cksghl1004/cpp_moondream2 with Docker Model Runner:
```
docker model run hf.co/cksghl1004/cpp_moondream2:F16
```

Lemonade

How to use cksghl1004/cpp_moondream2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cksghl1004/cpp_moondream2:F16

Run and chat with the model

lemonade run user.cpp_moondream2-F16

List all available models

lemonade list

Moondream is a small vision language model designed to run efficiently everywhere.

Website / Demo / GitHub

This repository contains the latest (2025-06-21) 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="2025-06-21",
    trust_remote_code=True,
    device_map={"": "cuda"}  # ...or 'mps', on Apple Silicon
)

# 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)")

Changelog

2025-06-21

(release notes coming soon)

2025-04-15 (full release notes)

Improved chart understanding (ChartQA up from 74.8 to 77.5, 82.2 with PoT)
Added temperature and nucleus sampling to reduce repetitive outputs
Better OCR for documents and tables (prompt with “Transcribe the text” or “Transcribe the text in natural reading order”)
Object detection supports document layout detection (figure, formula, text, etc)
UI understanding (ScreenSpot F1@0.5 up from 53.3 to 60.3)
Improved text understanding (DocVQA up from 76.5 to 79.3, TextVQA up from 74.6 to 76.3)

2025-03-27 (full release notes)

Added support for long-form captioning
Open vocabulary image tagging
Improved counting accuracy (e.g. CountBenchQA increased from 80 to 86.4)
Improved text understanding (e.g. OCRBench increased from 58.3 to 61.2)
Improved object detection, especially for small objects (e.g. COCO up from 30.5 to 51.2)
Fixed token streaming bug affecting multi-byte unicode characters
gpt-fast style compile() now supported in HF Transformers implementation

Downloads last month: 170

Safetensors

Model size

2B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

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