Phi-4-mini-instruct (3.8B)

Name: Phi-4-mini-instruct (3.8B)
Author: Microsoft Azure

Chat modelPhi-4

Release date: 2025-02-27Updated: 2025-02-28 08:35:59986

Live demoGitHubHugging Face Compare

Parameters

3.8B

Context length

128K

Chinese support

Supported

Reasoning ability

Phi-4-mini-instruct (3.8B) is an AI model published by Microsoft Azure, released on 2025-02-27, for Chat model, with 3.8B parameters, and 128K context length, requiring about 7.67GB storage, under the MIT License license, with a 88.60 score on GSM8K.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Phi-4-mini-instruct (3.8B)

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

No data

Model type

Chat model

Modality (in / out)

No data

Release date

2025-02-27

Model file size

7.67GB

MoE architecture

Total params / Active params

3.8B / N/A

Knowledge cutoff

No data

Phi-4-mini-instruct (3.8B)

Open source & experience

Code license

MIT License

Weights license

MIT License- 免费商用授权

GitHub repo

GitHub link unavailable

Hugging Face

https://huggingface.co/microsoft/Phi-4-mini-instruct

Live demo

No live demo

Phi-4-mini-instruct (3.8B)

Official resources

Paper

Empowering innovation: The next generation of the Phi family

DataLearnerAI blog

Phi-4-mini-instruct (3.8B)

API details

API speed

No data

No public API pricing yet.

Phi-4-mini-instruct (3.8B)

Benchmark Results

Phi-4-mini-instruct (3.8B) currently shows benchmark results led by GSM8K (14 / 26, score 88.60), HumanEval (24 / 39, score 74.40), MATH (27 / 42, score 64). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.