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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="grapevine-AI/phi-4-gguf",
	filename="phi-15B-4-BF16.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 grapevine-AI/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 grapevine-AI/phi-4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf grapevine-AI/phi-4-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf grapevine-AI/phi-4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf grapevine-AI/phi-4-gguf:Q4_K_M

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 grapevine-AI/phi-4-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf grapevine-AI/phi-4-gguf:Q4_K_M

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 grapevine-AI/phi-4-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf grapevine-AI/phi-4-gguf:Q4_K_M

Use Docker

docker model run hf.co/grapevine-AI/phi-4-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use grapevine-AI/phi-4-gguf with Ollama:
```
ollama run hf.co/grapevine-AI/phi-4-gguf:Q4_K_M
```

Unsloth Studio new

How to use grapevine-AI/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 grapevine-AI/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 grapevine-AI/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 grapevine-AI/phi-4-gguf to start chatting

Docker Model Runner
How to use grapevine-AI/phi-4-gguf with Docker Model Runner:
```
docker model run hf.co/grapevine-AI/phi-4-gguf:Q4_K_M
```

Lemonade

How to use grapevine-AI/phi-4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull grapevine-AI/phi-4-gguf:Q4_K_M

Run and chat with the model

lemonade run user.phi-4-gguf-Q4_K_M

List all available models

lemonade list

What is this?

Microsoft社開発のSLM（小型言語モデル）phi-4をGGUFフォーマットに変換したものです。
Unsloth.ai社の指摘により発覚したトークナイザ不具合の修正コミット（#21）を反映しております。

imatrix dataset

日本語能力を重視し、日本語が多量に含まれるTFMC/imatrix-dataset-for-japanese-llmデータセットを使用しました。
また、CUDA版llama.cppがbfloat16に対応したため、imatrixの算出は本来の数値精度であるBF16のモデルを使用して行いました。

Chat template

<|im_start|>system<|im_sep|>ここにSystem Promptを書きます<|im_end|><|im_start|>user<|im_sep|>ここにMessageを書きます<|im_end|><|im_start|>assistant<|im_sep|>

Note

llama.cpp-b4451以降と合わせてご利用ください。

Environment

Windows版llama.cpp-b4514およびllama.cpp-b4524同時リリースのconvert-hf-to-gguf.pyを使用して量子化作業を実施しました。

License

MIT

Developer

Microsoft Research

Downloads last month: 17

GGUF

Model size

15B params

Architecture

phi3

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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