Instructions to use kvignesh/phi4-mini-q8_0-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kvignesh/phi4-mini-q8_0-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kvignesh/phi4-mini-q8_0-gguf",
	filename="phi4-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use kvignesh/phi4-mini-q8_0-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 kvignesh/phi4-mini-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf kvignesh/phi4-mini-q8_0-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kvignesh/phi4-mini-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf kvignesh/phi4-mini-q8_0-gguf:Q8_0

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 kvignesh/phi4-mini-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf kvignesh/phi4-mini-q8_0-gguf:Q8_0

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 kvignesh/phi4-mini-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kvignesh/phi4-mini-q8_0-gguf:Q8_0

Use Docker

docker model run hf.co/kvignesh/phi4-mini-q8_0-gguf:Q8_0

LM Studio
Jan

vLLM

How to use kvignesh/phi4-mini-q8_0-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kvignesh/phi4-mini-q8_0-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": "kvignesh/phi4-mini-q8_0-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kvignesh/phi4-mini-q8_0-gguf:Q8_0

Ollama
How to use kvignesh/phi4-mini-q8_0-gguf with Ollama:
```
ollama run hf.co/kvignesh/phi4-mini-q8_0-gguf:Q8_0
```

Unsloth Studio

How to use kvignesh/phi4-mini-q8_0-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 kvignesh/phi4-mini-q8_0-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 kvignesh/phi4-mini-q8_0-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kvignesh/phi4-mini-q8_0-gguf to start chatting

How to use kvignesh/phi4-mini-q8_0-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kvignesh/phi4-mini-q8_0-gguf:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kvignesh/phi4-mini-q8_0-gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use kvignesh/phi4-mini-q8_0-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 kvignesh/phi4-mini-q8_0-gguf:Q8_0

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 kvignesh/phi4-mini-q8_0-gguf:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use kvignesh/phi4-mini-q8_0-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kvignesh/phi4-mini-q8_0-gguf:Q8_0

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 "kvignesh/phi4-mini-q8_0-gguf:Q8_0" \
  --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"

Docker Model Runner
How to use kvignesh/phi4-mini-q8_0-gguf with Docker Model Runner:
```
docker model run hf.co/kvignesh/phi4-mini-q8_0-gguf:Q8_0
```

Lemonade

How to use kvignesh/phi4-mini-q8_0-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kvignesh/phi4-mini-q8_0-gguf:Q8_0

Run and chat with the model

lemonade run user.phi4-mini-q8_0-gguf-Q8_0

List all available models

lemonade list

phi4-mini-q8_0-gguf / quantization_report.md

kvignesh

Upload folder using huggingface_hub

806c3d2 verified 20 days ago

preview code

Raw

History Blame Contribute Delete

3.52 kB

Quantization Report

Project Information

Item	Value
Model Name	Phi-4 Mini Instruct
Base Repository	microsoft/Phi-4-mini-instruct
Quantization Author	K VIGNESH
Quantization Framework	llama.cpp
Quantization Method	Post-Training Quantization (PTQ)
Quantization Type	Q8_0
Model Format	GGUF
Operating System	Windows 11
Hardware	Intel Core i7-1165G7
GPU Used	No

Objective

The objective of this project was to convert Microsoft's Phi-4 Mini Instruct model from Hugging Face Safetensors format to GGUF and apply Post-Training Quantization (PTQ) to reduce model size while maintaining inference quality.

The resulting model can be executed efficiently on CPU-only systems and is compatible with GGUF-supported inference engines.

Quantization Workflow

Phi-4 Mini Instruct (Safetensors)
                ↓
      GGUF Conversion (F16)
                ↓
 Post-Training Quantization (Q8_0)
                ↓
      Optimized GGUF Model

Step 1: Model Download

Downloaded the original model from Hugging Face:

microsoft/Phi-4-mini-instruct

Step 2: GGUF Conversion

Converted the Hugging Face Safetensors model to GGUF format using llama.cpp conversion utilities.

Output:

phi4-f16.gguf

Step 3: Quantization

Applied Q8_0 quantization using llama.cpp:

llama-quantize phi4-f16.gguf phi4-q8_0.gguf Q8_0

Output:

phi4-q8_0.gguf

Size Comparison

Model Version	Size
Original F16 GGUF	7.15 GB
Quantized Q8_0 GGUF	3.80 GB

Compression Achieved

Size Reduction ≈ 47%

Inference Validation

The quantized model was validated using llama.cpp.

Command:

llama-cli -m phi4-q8_0.gguf

The model successfully loaded and generated responses without requiring GPU acceleration.

Compatibility

This model is compatible with:

llama.cpp
Ollama
LM Studio
GPT4All
Jan
llama-cpp-python
Open WebUI

Advantages of Quantization

Reduced storage requirements
Lower memory consumption
Faster model loading
Improved deployment on consumer hardware
CPU-only execution support
Easier local deployment

Limitations

Minor accuracy degradation compared to full precision models
Quantized models may perform slightly differently on certain reasoning tasks
Performance depends on available CPU resources

Conclusion

The Phi-4 Mini Instruct model was successfully converted to GGUF format and quantized using the Q8_0 method.

The process reduced model size from approximately 7.15 GB to 3.80 GB while preserving usability for local inference workloads.

This quantized model is suitable for local AI applications, educational projects, research, and edge deployment scenarios.

Author

K VIGNESH

GGUF Conversion, Quantization, Validation, and Deployment Testing performed using llama.cpp.