Phi-4-multimodal-instruct

microsoft/Phi-4-multimodal-instruct

Speech Recognition5.6B parameterstransformersLicense: mit
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
195.7K
Total downloads
8.8M
Gained 7D
+52K(increase)
0.6%(up) vs baseline
Gained 30D
—
Likes
1,616
+0 in 7D
Rank · tracked models
#1,546
30(down 30 places)this week
Parameters
5.6B
Last source update
Dec 10, 2025
Momentum
61.7
  • Phi-4-multimodal-instruct gained 52K downloads during the last seven tracked days.
  • It moved from #107 to #109 among tracked Speech Recognition models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Phi-4-multimodal-instruct is a speech recognition model published by microsoft. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 2h ago.

Published
Feb 24, 2025
Last updated
Dec 10, 2025
Library
transformers
License
mit
Task
Speech Recognition
Parameters
5,574,460,384
Spaces
—
Derivative models
2
Velocity 7D/day
7,421
transformerssafetensorsphi4mmtext-generationnlpcodeaudioautomatic-speech-recognitionspeech-summarizationspeech-translationvisual-question-answeringphi-4-multimodal

Model family

Based on base-model relationships reported by the source's metadata.

Similar models

microsoft/Phi-4-multimodal-instruct — Downloads, Growth & Stats | OpenModelStats