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

Libraries

How to use llmware/phi-4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/phi-4-gguf",
	filename="phi-4-Q4_1.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 llmware/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 llmware/phi-4-gguf:Q4_1
# Run inference directly in the terminal:
llama-cli -hf llmware/phi-4-gguf:Q4_1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/phi-4-gguf:Q4_1
# Run inference directly in the terminal:
llama-cli -hf llmware/phi-4-gguf:Q4_1

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 llmware/phi-4-gguf:Q4_1
# Run inference directly in the terminal:
./llama-cli -hf llmware/phi-4-gguf:Q4_1

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 llmware/phi-4-gguf:Q4_1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/phi-4-gguf:Q4_1

Use Docker

docker model run hf.co/llmware/phi-4-gguf:Q4_1

LM Studio
Jan
Ollama
How to use llmware/phi-4-gguf with Ollama:
```
ollama run hf.co/llmware/phi-4-gguf:Q4_1
```

Unsloth Studio new

How to use llmware/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 llmware/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 llmware/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 llmware/phi-4-gguf to start chatting

Docker Model Runner
How to use llmware/phi-4-gguf with Docker Model Runner:
```
docker model run hf.co/llmware/phi-4-gguf:Q4_1
```

Lemonade

How to use llmware/phi-4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/phi-4-gguf:Q4_1

Run and chat with the model

lemonade run user.phi-4-gguf-Q4_1

List all available models

lemonade list

phi-4-gguf

phi-4-gguf is a GGUF Q4_K_M quantized version of Microsoft Phi-4, providing a fast, small inference implementation, optimized for AI PCs.

Model Description

Developed by: Microsoft
Quantized by: bartowksi
Model type: phi4
Parameters: 14.7 billion
Model Parent: microsoft/phi-4
Language(s) (NLP): English
License: Apache 2.0
Uses: Chat, general-purpose LLM
Quantization: int4

Model Card Contact

llmware on hf

llmware website

Downloads last month: 85

GGUF

Model size

15B params

Architecture

phi3

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for llmware/phi-4-gguf

Base model

microsoft/phi-4

Quantized

(149)

this model