Microsoft · Microsoft (Copilot / Phi)
Phi-4 Multimodal
ActiveVision-enabled ~14B Phi-4 variant that processes images alongside text; strong for on-device document and chart understanding.
About this version
Phi‑4 Multimodal is an open‑weight model in the Copilot family that extends the roughly 14 billion‑parameter Phi‑4 architecture with vision capabilities, allowing it to process images together with text. The addition of image input makes it well suited for on‑device tasks such as document and chart understanding, while retaining the core language abilities of earlier Phi‑4 releases.
- Tier
- Open Weight
Release & change timeline
No dated events logged for this version yet.
Patches, price changes, benchmarks, and deprecations for Phi-4 Multimodal will appear here as they’re recorded. Follow the broader Catch Me Up digest in the meantime.
Report an issue with Microsoft (Copilot / Phi)
Posts to your status feed
Pick the closest match below, edit the body, and post. Your report carries the #copilot tag automatically so it surfaces here + in the trending-tags rail. Reporting also follows Microsoft (Copilot / Phi) so you’ll get status updates.
Part of the Microsoft (Copilot / Phi) version timeline. Catch Me Up — everything that changed across AI & smart home ↗