Instructions to use jc-builds/Phi-4-mini-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jc-builds/Phi-4-mini-instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jc-builds/Phi-4-mini-instruct-GGUF",
	filename="Phi-4-mini-instruct-Q4_K_M.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 jc-builds/Phi-4-mini-instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jc-builds/Phi-4-mini-instruct-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 jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jc-builds/Phi-4-mini-instruct-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 jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jc-builds/Phi-4-mini-instruct-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 jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use jc-builds/Phi-4-mini-instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jc-builds/Phi-4-mini-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": "jc-builds/Phi-4-mini-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M

Ollama
How to use jc-builds/Phi-4-mini-instruct-GGUF with Ollama:
```
ollama run hf.co/jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use jc-builds/Phi-4-mini-instruct-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 jc-builds/Phi-4-mini-instruct-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 jc-builds/Phi-4-mini-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jc-builds/Phi-4-mini-instruct-GGUF to start chatting

Pi new

How to use jc-builds/Phi-4-mini-instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M

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": "jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jc-builds/Phi-4-mini-instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M

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 jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use jc-builds/Phi-4-mini-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M
```

Lemonade

How to use jc-builds/Phi-4-mini-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jc-builds/Phi-4-mini-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Phi-4-mini-instruct-GGUF-Q4_K_M

List all available models

lemonade list

Phi-4-mini-instruct — GGUF (iPhone-optimized)

GGUF quantizations of microsoft/Phi-4-mini-instruct, built and optimized for on-device inference on iPhone, iPad, and Apple Silicon Macs via llama.cpp or apps that wrap it (e.g. Haplo).

Built and quantized by jc-builds for the Haplo ecosystem. Original weights © Microsoft Corporation, redistributed under the MIT License per the upstream license.

TL;DR

A 3.8B-parameter reasoning-focused model from Microsoft. Punches well above its weight on math, code, and structured-reasoning benchmarks — beating models 5–10× its size on MATH and GPQA. 128k context with YaRN. MIT-licensed, the most permissive license among comparable models. Best small-model pick if you want "thinking mode" without paying the latency tax of a 7B+ model.

Available quantizations

File	Size	Bits/weight	Recommended use
`Phi-4-mini-instruct-Q4_K_M.gguf`	2.3 GB	4.8	Default — best size/quality tradeoff for phone & laptop
`Phi-4-mini-instruct-Q5_K_M.gguf`	2.6 GB	5.7	Slightly better reasoning, ~13% bigger; recommended for iPad / Mac
`Phi-4-mini-instruct-Q8_0.gguf`	3.8 GB	8.5	Near-FP16 quality; only worth it on Apple Silicon Mac

Pick Q4_K_M for general use. Phi-4-mini's reasoning quality holds up well at Q4_K_M. Avoid Q3 quants for this model — reasoning quality degrades noticeably.

Performance on Apple Silicon

Approximate decode throughput at single-batch greedy decode, 2048-token context. Measured with llama-cli.

Device	RAM	Q4_K_M tok/s	Notes
iPhone 15 Pro	8 GB	~18 tok/s	Smooth, but reasoning mode adds latency before the first token
iPhone 16 Pro	8 GB	~22 tok/s	Recommended phone target
iPad Pro M2	8 GB	~38 tok/s	Snappy
MacBook Pro M3	16 GB	~70 tok/s	Effectively instant

Reference numbers — Q5_K_M and Q8_0 are roughly 15% / 40% slower than Q4_K_M.

How to use

1. Haplo (iPhone / iPad / Mac)

The model appears automatically in Haplo's model browser on Kuzco-1.1.0+ builds. The download URL for Q4_K_M is:

https://huggingface.co/jc-builds/Phi-4-mini-instruct-GGUF/resolve/main/Phi-4-mini-instruct-Q4_K_M.gguf

2. llama.cpp (CLI)

huggingface-cli download jc-builds/Phi-4-mini-instruct-GGUF Phi-4-mini-instruct-Q4_K_M.gguf --local-dir .

./llama-cli \
  -m Phi-4-mini-instruct-Q4_K_M.gguf \
  -p "If x^2 + 3x - 10 = 0, find x." \
  -n 512 \
  --temp 0.0

For reasoning-heavy tasks set --temp 0.0 and let the model deterministically work through the problem.

3. Ollama

cat <<'EOF' > Modelfile
FROM ./Phi-4-mini-instruct-Q4_K_M.gguf
PARAMETER temperature 0.0
PARAMETER top_p 1.0
EOF
ollama create phi-4-mini -f Modelfile
ollama run phi-4-mini

Long context (128k via YaRN)

Phi-4-mini is trained at 64k context and can stretch to 128k tokens via YaRN extrapolation. To enable: most clients pick this up automatically from the GGUF metadata. If yours doesn't, set --rope-scaling yarn --rope-scale 2.0 in llama.cpp.

Sampling defaults

For reasoning tasks (math, code, structured output): temperature=0.0, top_p=1.0. For chat / general output: temperature=0.7, top_p=0.9.

The GGUF stores no defaults — pass them explicitly per task.

Chat template

Phi-4-mini uses the Phi-3 chat template. The tokenizer stores it in the GGUF metadata, so llama.cpp's --chat-template flag isn't required.

<|system|>
{system}<|end|>
<|user|>
{user}<|end|>
<|assistant|>
{assistant}<|end|>

Quantization recipe

Built with llama.cpp at commit e43431b (May 7, 2026).

Downloaded microsoft/Phi-4-mini-instruct safetensors checkpoint via huggingface-cli.
Converted to GGUF FP16 via convert_hf_to_gguf.py --outtype f16 (Phi-4 reuses the Phi-3 architecture path in convert).

Quantized to each target type via llama-quantize:

llama-quantize Phi-4-mini-F16.gguf Phi-4-mini-instruct-Q4_K_M.gguf Q4_K_M
llama-quantize Phi-4-mini-F16.gguf Phi-4-mini-instruct-Q5_K_M.gguf Q5_K_M
llama-quantize Phi-4-mini-F16.gguf Phi-4-mini-instruct-Q8_0.gguf   Q8_0

No imatrix calibration was used — the weights come from the upstream FP16 directly.

Original model card

See the upstream model card for full architecture, training, benchmarks, and Microsoft's responsible-AI guidance: microsoft/Phi-4-mini-instruct.

License

MIT License, inherited from the original model — the most permissive license among comparable on-device models. Commercial use, modification, redistribution, and bundling in proprietary apps are all permitted with attribution. See LICENSE for full terms.

Phi-4-mini by Microsoft Corporation. Licensed under the MIT License.

Acknowledgements

Microsoft for the original Phi-4-mini weights and an unusually open-licensed release.
The llama.cpp team for the GGUF format and quantization tooling.
The Haplo ecosystem this drop is built for.

Downloads last month: 352

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for jc-builds/Phi-4-mini-instruct-GGUF

Base model

microsoft/Phi-4-mini-instruct

Quantized

(147)

this model