Instructions to use Jooju2872/moondream2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Jooju2872/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 Jooju2872/moondream2:F16
# Run inference directly in the terminal:
llama cli -hf Jooju2872/moondream2:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Jooju2872/moondream2:F16
# Run inference directly in the terminal:
llama cli -hf Jooju2872/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 Jooju2872/moondream2:F16
# Run inference directly in the terminal:
./llama-cli -hf Jooju2872/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 Jooju2872/moondream2:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Jooju2872/moondream2:F16

Use Docker

docker model run hf.co/Jooju2872/moondream2:F16

LM Studio
Jan

vLLM

How to use Jooju2872/moondream2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jooju2872/moondream2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jooju2872/moondream2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jooju2872/moondream2:F16

Ollama
How to use Jooju2872/moondream2 with Ollama:
```
ollama run hf.co/Jooju2872/moondream2:F16
```

Unsloth Studio

How to use Jooju2872/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 Jooju2872/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 Jooju2872/moondream2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Jooju2872/moondream2 to start chatting

Atomic Chat new
Docker Model Runner
How to use Jooju2872/moondream2 with Docker Model Runner:
```
docker model run hf.co/Jooju2872/moondream2:F16
```

Lemonade

How to use Jooju2872/moondream2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Jooju2872/moondream2:F16

Run and chat with the model

lemonade run user.moondream2-F16

List all available models

lemonade list

Jooju2872 commited on May 13, 2025

Commit

bf3f47b

verified ·

1 Parent(s): c3c60cc

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -5,6 +5,9 @@ pipeline_tag: image-text-to-text
 moondream is a small vision language model designed to run efficiently on edge devices. Check out the [GitHub repository](https://github.com/vikhyat/moondream) for details, or try it out on the [Hugging Face Space](https://huggingface.co/spaces/vikhyatk/moondream2)!
 **Benchmarks**
 | Release | VQAv2 | GQA | TextVQA | DocVQA | TallyQA<br>(simple/full) | POPE<br>(rand/pop/adv) |

 moondream is a small vision language model designed to run efficiently on edge devices. Check out the [GitHub repository](https://github.com/vikhyat/moondream) for details, or try it out on the [Hugging Face Space](https://huggingface.co/spaces/vikhyatk/moondream2)!
+> [!NOTE]
+> This model works on lower Torch version(2.1.1) and adds `temperature` and `top_p` parameters.
 **Benchmarks**
 | Release | VQAv2 | GQA | TextVQA | DocVQA | TallyQA<br>(simple/full) | POPE<br>(rand/pop/adv) |