Models / microsoft / Phi-4 Multimodal Instruct

Phi-4 Multimodal Instruct

JSON →
multimodal

A multimodal instruction-tuned model from Microsoft Phi-4 family capable of processing text, images, and audio.

textimageaudiovisionstreamingreasoningcode-generationfunction-calling
Specs
Context & limits
131K
context window
4K
max output
Lifecycle
Dates
released2025-02-01
knowledge cutoff2024-06-01
Resources