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

Libraries

How to use microsoft/Phi-4-mini-instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="microsoft/Phi-4-mini-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-4-mini-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-mini-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Phi-4-mini-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Phi-4-mini-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-4-mini-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-4-mini-instruct

SGLang

How to use microsoft/Phi-4-mini-instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "microsoft/Phi-4-mini-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-4-mini-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "microsoft/Phi-4-mini-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-4-mini-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

If you having issues with this Model use either ONNX versions or convert this model.

#34

by brentrynn - opened Jun 30, 2025

Discussion

brentrynn

Jun 30, 2025

This model works best if you use ONNX for inference. If you’re having issues, try running an ONNX version—it seems to work a lot better. I thought I’d post this here since a lot of people are struggling to get this model working.

However, it won’t work out-of-the-box unless you patch the build script to allow conversion. I’m uploading my scripts so anyone can use them. You’ll also need to clean up all the arrays in the JSON files (basically, just convert nested arrays to flat arrays).

I had to rebuild with this command to make inference work:

python -m onnxruntime_genai.models.builder
-m Phi
-o models
-p fp16
-e cuda
--extra_options num_attention_heads=24 num_key_value_heads=8

Not sure if this will help anyone else, but you can find all the scripts and fixes on my GitHub:

https://github.com/brentrynn/phi-onnx

brentrynn

Jul 6, 2025

I should add there is a ONNX model on here you can use and that works out of the box.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment