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

Libraries

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

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

pipe = pipeline("text-generation", model="microsoft/Phi-4-mini-flash-reasoning")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("microsoft/Phi-4-mini-flash-reasoning", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Phi-4-mini-flash-reasoning 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-flash-reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-4-mini-flash-reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use microsoft/Phi-4-mini-flash-reasoning 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-flash-reasoning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-4-mini-flash-reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-flash-reasoning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-4-mini-flash-reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

hmellor HF Staff commited on Aug 12, 2025

Commit

f92f7ac

verified ·

1 Parent(s): 88bd2a6

Fix typo in `configuration_phi4flash.py`

Browse files

Files changed (1) hide show

configuration_phi4flash.py +1 -1

configuration_phi4flash.py CHANGED Viewed

@@ -146,7 +146,7 @@ class Phi4FlashConfig(PretrainedConfig):
         self.layer_types = layer_types
         if self.layer_types is None:
-            is_sliding = lambda i: i < num_hidden_layers // 2 and i % 2 == 1,
             self.layer_types = [
                 "sliding_attention" if is_sliding(layer_idx) else "full_attention"
                 for layer_idx in range(num_hidden_layers)

         self.layer_types = layer_types
         if self.layer_types is None:
+            is_sliding = lambda i: i < num_hidden_layers // 2 and i % 2 == 1
             self.layer_types = [
                 "sliding_attention" if is_sliding(layer_idx) else "full_attention"
                 for layer_idx in range(num_hidden_layers)