Instructions to use crystalai35/moondream-1.8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use crystalai35/moondream-1.8b 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 crystalai35/moondream-1.8b:F16
# Run inference directly in the terminal:
llama cli -hf crystalai35/moondream-1.8b:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf crystalai35/moondream-1.8b:F16
# Run inference directly in the terminal:
llama cli -hf crystalai35/moondream-1.8b: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 crystalai35/moondream-1.8b:F16
# Run inference directly in the terminal:
./llama-cli -hf crystalai35/moondream-1.8b: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 crystalai35/moondream-1.8b:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf crystalai35/moondream-1.8b:F16

Use Docker

docker model run hf.co/crystalai35/moondream-1.8b:F16

LM Studio
Jan
Ollama
How to use crystalai35/moondream-1.8b with Ollama:
```
ollama run hf.co/crystalai35/moondream-1.8b:F16
```

Unsloth Studio

How to use crystalai35/moondream-1.8b 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 crystalai35/moondream-1.8b 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 crystalai35/moondream-1.8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for crystalai35/moondream-1.8b to start chatting

Docker Model Runner
How to use crystalai35/moondream-1.8b with Docker Model Runner:
```
docker model run hf.co/crystalai35/moondream-1.8b:F16
```

Lemonade

How to use crystalai35/moondream-1.8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull crystalai35/moondream-1.8b:F16

Run and chat with the model

lemonade run user.moondream-1.8b-F16

List all available models

lemonade list

Atomic Chat

Moondream 1.8B GGUF

Vision-language model for image understanding.

Files

moondream-1.8b.gguf - Main text model
moondream-mmproj-f16.gguf - Vision encoder projector

Usage with Ollama

```bash ollama run yourusername/moondream ```

Downloads last month: 126

GGUF

Model size

1B params

Architecture

phi2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for crystalai35/moondream-1.8b

Base model

vikhyatk/moondream2

Quantized

(7)

this model