Instructions to use mackkkkkilllll/MediPhi-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/MediPhi-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/MediPhi-Instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf mackkkkkilllll/MediPhi-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/MediPhi-Instruct-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf mackkkkkilllll/MediPhi-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/MediPhi-Instruct-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf mackkkkkilllll/MediPhi-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/MediPhi-Instruct-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mackkkkkilllll/MediPhi-Instruct-GGUF:F16

Use Docker

docker model run hf.co/mackkkkkilllll/MediPhi-Instruct-GGUF:F16

LM Studio
Jan

vLLM

How to use mackkkkkilllll/MediPhi-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mackkkkkilllll/MediPhi-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/MediPhi-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mackkkkkilllll/MediPhi-Instruct-GGUF:F16

Ollama
How to use mackkkkkilllll/MediPhi-Instruct-GGUF with Ollama:
```
ollama run hf.co/mackkkkkilllll/MediPhi-Instruct-GGUF:F16
```
Unsloth Desktop
Docker Model Runner
How to use mackkkkkilllll/MediPhi-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/mackkkkkilllll/MediPhi-Instruct-GGUF:F16
```

Lemonade

How to use mackkkkkilllll/MediPhi-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mackkkkkilllll/MediPhi-Instruct-GGUF:F16

Run and chat with the model

lemonade run user.MediPhi-Instruct-GGUF-F16

List all available models

lemonade list

Atomic Chat

MediPhi-Instruct GGUF

GGUF versions of MediPhi-Instruct prepared for local inference.

This repository provides both an F16 version and a Q4_K_M quantized version for use with llama.cpp and other GGUF-compatible inference engines.

Available Files

File	Format	Approx. Size
`MediPhi-Instruct-F16.gguf`	F16	7.2 GB
`MediPhi-Instruct-Q4_K_M.gguf`	Q4_K_M	2.3 GB

Recommended Version

MediPhi-Instruct-Q4_K_M.gguf is recommended for most local inference setups because it requires substantially less memory than the F16 version.

The F16 version is provided when higher precision is preferred and sufficient memory is available.

Quantization

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

Quantization format:

Q4_K_M

llama.cpp

Basic usage:

llama-cli -m MediPhi-Instruct-Q4_K_M.gguf

GPU offloading:

llama-cli -m MediPhi-Instruct-Q4_K_M.gguf -ngl 99

Local server:

llama-server -m MediPhi-Instruct-Q4_K_M.gguf -ngl 99

Compatible Software

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

Original Model

This repository contains a community GGUF conversion and quantization of MediPhi-Instruct.

Original model:

PLACE_ORIGINAL_MODEL_URL_HERE

Please refer to the original model repository for the model license, intended use, limitations, and attribution requirements.

Disclaimer

This repository is not an official repository of the original model authors unless explicitly stated.

SHA256

Checksums can be generated with:

sha256sum *.gguf

Downloads last month: 114

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

4-bit

16-bit