Instructions to use senthilsdglakhsg/phi3-Q4.gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use senthilsdglakhsg/phi3-Q4.gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="senthilsdglakhsg/phi3-Q4.gguf",
	filename="phi3-Q4.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use senthilsdglakhsg/phi3-Q4.gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf senthilsdglakhsg/phi3-Q4.gguf
# Run inference directly in the terminal:
llama-cli -hf senthilsdglakhsg/phi3-Q4.gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf senthilsdglakhsg/phi3-Q4.gguf
# Run inference directly in the terminal:
llama-cli -hf senthilsdglakhsg/phi3-Q4.gguf

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 senthilsdglakhsg/phi3-Q4.gguf
# Run inference directly in the terminal:
./llama-cli -hf senthilsdglakhsg/phi3-Q4.gguf

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 senthilsdglakhsg/phi3-Q4.gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf senthilsdglakhsg/phi3-Q4.gguf

Use Docker

docker model run hf.co/senthilsdglakhsg/phi3-Q4.gguf

LM Studio
Jan

vLLM

How to use senthilsdglakhsg/phi3-Q4.gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "senthilsdglakhsg/phi3-Q4.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": "senthilsdglakhsg/phi3-Q4.gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/senthilsdglakhsg/phi3-Q4.gguf

Ollama
How to use senthilsdglakhsg/phi3-Q4.gguf with Ollama:
```
ollama run hf.co/senthilsdglakhsg/phi3-Q4.gguf
```

Unsloth Studio new

How to use senthilsdglakhsg/phi3-Q4.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 senthilsdglakhsg/phi3-Q4.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 senthilsdglakhsg/phi3-Q4.gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for senthilsdglakhsg/phi3-Q4.gguf to start chatting

Docker Model Runner
How to use senthilsdglakhsg/phi3-Q4.gguf with Docker Model Runner:
```
docker model run hf.co/senthilsdglakhsg/phi3-Q4.gguf
```

Lemonade

How to use senthilsdglakhsg/phi3-Q4.gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull senthilsdglakhsg/phi3-Q4.gguf

Run and chat with the model

lemonade run user.phi3-Q4.gguf-{{QUANT_TAG}}

List all available models

lemonade list

Phi-3 Mini (GGUF Quantized - Q4_K_M)

Model Description

This repository contains a quantized GGUF version of the Phi-3 Mini 128K Instruct model.

Base Model: microsoft/Phi-3-mini-128k-instruct
Format: GGUF
Quantization: Q4_K_M
Framework: llama.cpp

This model is optimized for efficient local inference with reduced memory usage.

Intended Use

Local LLM inference
Chatbots
Lightweight deployments
CPU/GPU inference using llama.cpp

Model Details

Base Model

Microsoft Phi-3 Mini (128K context)

Conversion

Converted from Hugging Face format → GGUF

Quantization

Method: Q4_K_M
Tool: llama.cpp quantize

This reduces model size while maintaining reasonable performance.

How to Use

Using llama.cpp

./llama-cli -m model-q4.gguf -p "Explain AI simply"

Downloads last month: 139

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants