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", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-mini-flash-reasoning", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-4-mini-flash-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-4-mini-flash-reasoning",
		"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-flash-reasoning" \
        --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-flash-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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
```

Phi-4-mini-flash-reasoning

Commit History

Jul 17, 2025

13:21
Improve model card: Add paper abstract for Phi-4-mini-flash-reasoning⁠

nielsr HF Staff

Verified signature
0868e47

Jul 15, 2025

07:56
Update README.md

renll

Verified signature
486d7c3

Jul 14, 2025

20:00
Update README.md

renll

Verified signature
fc31dd3
19:59
Add training codebase link mentioned in paper abstract (#3)⁠

renll +1: nielsr

Verified signature
dcf4f08

Jul 11, 2025

05:44
Update README.md

renll

Verified signature
0c2b39f

Jul 10, 2025

20:35
Update README.md

renll

Verified signature
98fd671

Jul 9, 2025

20:09
Update README.md

renll

Verified signature
98a8001
16:16
Update README.md

renll

Verified signature
43aab46
07:37
Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

renll

Verified signature
a830f22
07:37
Delete Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation.pdf

renll

Verified signature
b5116f9
07:35
Delete Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

renll

Verified signature
6f94ac5
07:34
Upload Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation.pdf

renll

Verified signature
d847d2d

Jul 8, 2025

23:34
Update README.md

renll

Verified signature
b240aa7
19:34
Update README.md

renll

Verified signature
5140046
08:24
Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

renll

Verified signature
ebfff50
07:56
Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

renll

Verified signature
375bfc2

Jul 4, 2025

23:50
Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

renll

Verified signature
cca57de
10:18
Delete Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation.pdf

renll

Verified signature
9444ff6
10:18
Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

renll

Verified signature
6d6acda

Jun 30, 2025

23:17
Upload Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation.pdf

renll

Verified signature
1f8307a
20:58
Update README.md

renll

Verified signature
1f168f5
20:08
Update README.md

renll

Verified signature
cddb27e
20:07
Update README.md

renll

Verified signature
e49b6ce

Jun 26, 2025

05:27
Update README.md

renll

Verified signature
a24e8b9

Jun 25, 2025

05:29
Update README.md

renll

Verified signature
44171ba

Jun 24, 2025

03:19
Update README.md

renll

Verified signature
f1114ff

Jun 23, 2025

21:33
Update README.md

renll

Verified signature
ed7b17d
21:29
Update README.md

renll

Verified signature
a5d1907
21:27
Update README.md

renll

Verified signature
2840921
21:26
Update README.md

renll

Verified signature
f3746df
19:37
Update README.md

renll

Verified signature
5bf09df

Jun 22, 2025

09:54
Update README.md

renll

Verified signature
068f2c0
09:52
Update README.md

renll

Verified signature
452fd5f
09:51
Upload README.md

renll

Verified signature
a892bba
09:43
Upload 3 files

renll

Verified signature
47c33b0
08:41
Upload 5 files

renll

Verified signature
0fdaec1
08:26
Upload 3 files

renll

Verified signature
3c17a22
08:19
Upload 12 files

renll

Verified signature
86604fc

Jun 19, 2025

23:40
initial commit

renll

Verified signature
590843e

Commit History

Jul 17, 2025

Improve model card: Add paper abstract for Phi-4-mini-flash-reasoning⁠

Jul 15, 2025

Update README.md

Jul 14, 2025

Update README.md

Add training codebase link mentioned in paper abstract (#3)⁠

Jul 11, 2025

Update README.md

Jul 10, 2025

Update README.md

Jul 9, 2025

Update README.md

Update README.md

Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

Delete Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation.pdf

Delete Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

Upload Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation.pdf

Jul 8, 2025

Update README.md

Update README.md

Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

Jul 4, 2025

Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

Delete Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation.pdf

Upload Decoder_Hybrid_Decoder_Architecture_for_Efficient_Reasoning_with_Long_Generation.pdf

Jun 30, 2025

Upload Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation.pdf

Update README.md

Update README.md

Update README.md

Jun 26, 2025

Update README.md

Jun 25, 2025

Update README.md

Jun 24, 2025

Update README.md

Jun 23, 2025

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Jun 22, 2025

Update README.md

Update README.md

Upload README.md

Upload 3 files

Upload 5 files

Upload 3 files

Upload 12 files

Jun 19, 2025

initial commit