Skip to main content

Phi4-mini

Demonstration Environment

Development Board : Jetson Orin Series Board

warning

Due to performance limitations, this model cannot be run on the Jetson Orin Nano 4GB.

The Phi-4-mini-instruction is a lightweight, open model built on synthetic data and curated public websites, focusing on high-quality, inference-intensive data.

1. Model Scale​

ModelVolume
phi4-mini:3.8b2.5GB

2. Performance​

Screenshot

3. Using Phi4-mini​

3.1 Running Phi4-mini​

Use the run command to start running the model. If the model has not been downloaded, it will automatically pull the model from the Ollama model library:

ollama run phi4-mini:3.8b

Screenshot

3.2 Starting a Conversation​

How many minutes is a quarter of an hour?

Response time depends on your hardware configuration. Please be patient!

Screenshot

3.3 Ending a Conversation​

Use the Ctrl+D shortcut or /bye to end a conversation!

References​

Ollama

Official Website: https://ollama.com/

GitHub: https://github.com/ollama/ollama

Phi4-mini

Ollama Compatible Model: https://ollama.com/library/phi4-mini