Local AI with Phi 4 inference snap
Phi 4 is a 14B parameter state-of-the-art open model by Microsoft, built upon a blend
of synthetic datasets, filtered public domain websites, and academic books and Q&A
datasets, focused on high quality data and advanced reasoning.
Use this snap to quickly install an optimized environment for local inference with Phi 4.
The snap includes the following hardware-optimized inference engines:
- cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
- nvidia-gpu: CUDA-enabled GPU acceleration
The most suitable engine is automatically selected based on the available hardware.
Install:
sudo snap install phi4
Run:
phi4
Some accelerators require extra drivers to be usable with this snap:
https://documentation.ubuntu.com/inference-snaps/how-to/setup/drivers/
License:
The Phi 4 model is provided by Microsoft under the MIT license.
The licenses of all the bundled software can be found after installing the snap at
/snap/phi4/current/usr/share/doc.