InterconnectsArtifacts Hub
withVAILVAIL
All models

Phi-4-multimodal-instruct

byMicrosoftMicrosoft· 24 Feb 2025
General purposeMultimodal

An update to Phi, supporting text, images and audio as input.

Specs
Params5.6B
LicenseMIT
Tags
modelsmodels/llmsmodels/llms/multi-modalmodels/llms/reasoningmultilingualartifacts/8
Resources
Hugging Face — microsoft/Phi-4-multimodal-instructPaper / tech reportAppeared in Artifacts Log #8
Capability · Artificial Analysis
AA Index
4.5
Adoption · Interconnects
RAM score
—
Hugging Face Downloads
536K
last 30d
7.7M
all time
HF Likes
1.6K

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Related Models

More from Microsoft

FastContext-1.0-4B-SFT
MicrosoftMicrosoft14 Jun 2026
Phi-4-reasoning-vision-15B
MicrosoftMicrosoft04 Mar 2026
Fara-7B
MicrosoftMicrosoft24 Nov 2025
VibeVoice-1.5B
MicrosoftMicrosoft25 Aug 2025

Similar Models

RoboBrain2.0-7B
BAAIBAAI06 Jun 2025
NuMarkdown-8B-Thinking
numindnumind29 Jul 2025
AgentCPM-GUI
OpenBMBOpenBMB13 May 2025
Chandra OCR 2
datalab-todatalab-to16 Mar 2026