Phi-4-multimodal

A Microsoft 5.6B parameter model that processes speech, images and text in a single architecture with a mixture of LoRAs. Handles speech recognition and translation, OCR, chart and table interpretation, and multi-image comparison.

Understands

text, images, audio

Produces

text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.