Instructions to use mackkkkkilllll/Phi-4-mini-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mackkkkkilllll/Phi-4-mini-instruct-GGUF 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 mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf mackkkkkilllll/Phi-4-mini-instruct-GGUF: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 mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf mackkkkkilllll/Phi-4-mini-instruct-GGUF: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 mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

Use Docker

docker model run hf.co/mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

LM Studio
Jan

vLLM

How to use mackkkkkilllll/Phi-4-mini-instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mackkkkkilllll/Phi-4-mini-instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mackkkkkilllll/Phi-4-mini-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

Ollama
How to use mackkkkkilllll/Phi-4-mini-instruct-GGUF with Ollama:
```
ollama run hf.co/mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16
```
Unsloth Desktop

How to use mackkkkkilllll/Phi-4-mini-instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mackkkkkilllll/Phi-4-mini-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16
```

Lemonade

How to use mackkkkkilllll/Phi-4-mini-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

Run and chat with the model

lemonade run user.Phi-4-mini-instruct-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use mackkkkkilllll/Phi-4-mini-instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mackkkkkilllll/Phi-4-mini-instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "mackkkkkilllll/Phi-4-mini-instruct-GGUF:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Phi-4-mini-instruct GGUF

GGUF versions of Microsoft Phi-4-mini-instruct prepared for efficient local inference.

This repository contains an F16 GGUF version and a Q4_K_M quantized version.

Available Files

File	Format	Approx. Size
`Phi-4-mini-instruct-F16.gguf`	F16	7.2 GB
`Phi-4-mini-instruct-Q4_K_M.gguf`	Q4_K_M	2.4 GB

Recommended Version

Phi-4-mini-instruct-Q4_K_M.gguf is recommended for most consumer hardware and local inference setups.

It provides a substantially smaller memory footprint than F16 while retaining the advantages of the GGUF format.

Original Model

The original model is Microsoft's official Phi-4-mini-instruct.

Original model:

https://huggingface.co/microsoft/Phi-4-mini-instruct

Please refer to Microsoft's original model repository for technical details, intended use, limitations, and licensing.

Quantization

The Q4_K_M file was generated from the F16 GGUF model using llama.cpp quantization tools.

Quantization format:

Q4_K_M

llama.cpp

Basic usage:

llama-cli -m Phi-4-mini-instruct-Q4_K_M.gguf

GPU offloading:

llama-cli -m Phi-4-mini-instruct-Q4_K_M.gguf -ngl 99

Local server:

llama-server -m Phi-4-mini-instruct-Q4_K_M.gguf -ngl 99

Compatible Software

llama.cpp
llama-cpp-python
LM Studio
Jan
Other GGUF-compatible runtimes

Model Variants

F16

Higher precision with substantially larger memory requirements.

Q4_K_M

Smaller model size and lower memory requirements, making it more suitable for local deployment on consumer hardware.

Disclaimer

This is a community GGUF conversion and quantization. It is not an official Microsoft repository.

License

Please follow the licensing terms of the original Microsoft Phi-4-mini-instruct model.

SHA256

Checksums can be generated with:

sha256sum *.gguf

Downloads last month: 139

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

4-bit

16-bit