Instructions to use AI-Engine/phi-4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AI-Engine/phi-4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AI-Engine/phi-4-GGUF",
	filename="phi-4-IQ4_XS.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 AI-Engine/phi-4-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AI-Engine/phi-4-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama-cli -hf AI-Engine/phi-4-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AI-Engine/phi-4-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama-cli -hf AI-Engine/phi-4-GGUF:IQ4_XS

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 AI-Engine/phi-4-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf AI-Engine/phi-4-GGUF:IQ4_XS

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 AI-Engine/phi-4-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AI-Engine/phi-4-GGUF:IQ4_XS

Use Docker

docker model run hf.co/AI-Engine/phi-4-GGUF:IQ4_XS

LM Studio
Jan
Ollama
How to use AI-Engine/phi-4-GGUF with Ollama:
```
ollama run hf.co/AI-Engine/phi-4-GGUF:IQ4_XS
```

Unsloth Studio new

How to use AI-Engine/phi-4-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 AI-Engine/phi-4-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 AI-Engine/phi-4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AI-Engine/phi-4-GGUF to start chatting

Docker Model Runner
How to use AI-Engine/phi-4-GGUF with Docker Model Runner:
```
docker model run hf.co/AI-Engine/phi-4-GGUF:IQ4_XS
```

Lemonade

How to use AI-Engine/phi-4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AI-Engine/phi-4-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.phi-4-GGUF-IQ4_XS

List all available models

lemonade list

GGUF llama.cpp quantized version of:

Original model: phi-4
Model creator: Microsoft
License

Recommended Prompt Format (phi-4)

<|im_start|>system<|im_sep|>
You are a medieval knight and must provide explanations to modern people.<|im_end|>
<|im_start|>user<|im_sep|>
How should I explain the Internet?<|im_end|>
<|im_start|>assistant<|im_sep|>

Downloads last month: 2

GGUF

Model size

15B params

Architecture

phi3

Hardware compatibility

4-bit

5-bit

Inference Providers NEW

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