Instructions to use satviksrivas7/openphone-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use satviksrivas7/openphone-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="satviksrivas7/openphone-gguf",
	filename="openphone-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use satviksrivas7/openphone-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf satviksrivas7/openphone-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf satviksrivas7/openphone-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf satviksrivas7/openphone-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf satviksrivas7/openphone-gguf:Q4_K_M

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 satviksrivas7/openphone-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf satviksrivas7/openphone-gguf:Q4_K_M

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 satviksrivas7/openphone-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf satviksrivas7/openphone-gguf:Q4_K_M

Use Docker

docker model run hf.co/satviksrivas7/openphone-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use satviksrivas7/openphone-gguf with Ollama:
```
ollama run hf.co/satviksrivas7/openphone-gguf:Q4_K_M
```

Unsloth Studio

How to use satviksrivas7/openphone-gguf 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 satviksrivas7/openphone-gguf 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 satviksrivas7/openphone-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for satviksrivas7/openphone-gguf to start chatting

Docker Model Runner
How to use satviksrivas7/openphone-gguf with Docker Model Runner:
```
docker model run hf.co/satviksrivas7/openphone-gguf:Q4_K_M
```

Lemonade

How to use satviksrivas7/openphone-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull satviksrivas7/openphone-gguf:Q4_K_M

Run and chat with the model

lemonade run user.openphone-gguf-Q4_K_M

List all available models

lemonade list

OpenPhone Model - Q4_K_M GGUF

This is a quantized GGUF version of the HKUDS/OpenPhone model.

Model Details

Base Model: HKUDS/OpenPhone (3B parameter vision-language model)
Quantization: Q4_K_M
Format: GGUF
File Size: ~1.8GB (quantized from ~7GB)
Architecture: Qwen2.5-VL

About OpenPhone

OpenPhone is an open-source mobile AI agent model designed for on-device smartphone interaction. It's optimized for mobile GUI tasks and edge device deployment.

Usage

This GGUF model can be used with llama.cpp and compatible inference engines that support GGUF format.

# Example usage with llama.cpp
./llama-cli -m openphone-q4_k_m.gguf -p "Your prompt here"

satviksrivas7
/

openphone-gguf

OpenPhone Model - Q4_K_M GGUF

Model Details

About OpenPhone

Usage

Links