multimodal LLM
Phi-4-reasoning-vision-15B
Microsoft's 15B reasoning model with vision; no Phi-5 found on HF as of 2026-10-10.
Levelmodel
Classmultimodal LLM
Parameters15B
Context16,384
Released4 Mar 2026
Opennessopen weights permissive
Runs onconsumer GPU
Statusactive
Benchmark Results
vendor-reported
AI2Dmultimodal
vendor-reported
84.8
050100
Score in %. Higher is better.
MMMUmultimodal
vendor-reported
54.3
050100
Score in %. Higher is better.
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
finetune
Phi-4-reasoning is the parent (finetune)medium confidencemodel cardWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
- Developer
- Microsoft AI
- Family
- not in the notes
- Released
- 4 Mar 2026 sourcesnotes
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer Dense, SigLIP-2 vision encoder
- Total parameters
- 15B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- 16,384 tokens
- Input
- text, image
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- consumer GPU
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperMicrosoft AIbig tech, USA
Microsoft AIbig tech, USAModelPhi-4-reasoning-vision-15BMicrosoft AI, multimodal LLM
Phi-4-reasoning-vision-15BMicrosoft AI, multimodal LLMR&D TopicsVisual Instruction Tuning
Use CasesRobot Inspection with Instrument ReadingIndustrialPathology Whole-Slide ImagingHealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Organisations 1
Sources
- huggingface.co/microsoft/Phi-4-reasoning-vision-15B https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B
- huggingface.co/microsoft/models?search=phi https://huggingface.co/microsoft/models?search=phi
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Phi-4-Reasoning-Vision-15B", https://aurion.semai.id/models/microsoft-phi-4-reasoning-vision-15b/, records of October 2026.