llm.create_chat_completion(
messages = "No input example has been defined for this model task."
)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"
Links
- GitHub: https://github.com/HKUDS/OpenPhone
- Base Model: https://huggingface.co/hkhuds/onephone
- Downloads last month
- 2
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# !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", )