Phi 4 (phi4)
Install latest/stable of Phi 4
Ubuntu 16.04 or later?
Make sure snap support is enabled in your Desktop store.
Details for Phi 4
Package name
- phi4
License
- unset
Last updated
- 23 September 2026 - latest/stable
- 23 September 2026 - latest/beta
Websites
Source code
Report a bug
External link warning
You are about to open
Do you wish to proceed?
Report a Snap Store violation
Report Phi 4 for a Snap Store violation
Snap Store Violation Report submitted successfully
Thank you for your report. Information you provided will help us investigate further.
Error submitting report
There was an error while sending your report. Please try again later.
Share this snap
Generate an embeddable card to be shared on external websites.
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.
| Revision | Channel | Version | Build | Commit | Download SBOM |
|---|
The build and commit information is derived from build infrastructure records.
Install Phi 4 on your Linux distribution
Choose your Linux distribution to get detailed installation instructions. If yours is not shown, get more details on the installing snapd documentation.
