vision
MobileSAM
Lightweight Segment Anything for mobile applications, with a distilled small image encoder.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released25 Jun 2023
Opennessunknown
Runs onmobile or NPU
Statusactive
R&D Topics
Identity
- Developer
- Kyung Hee University
- Family
- not in the notes
- Released
- 25 Jun 2023 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 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
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image
- Output
- image
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
- unknown
- Licence
- not in the notes sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- mobile or NPU
- Footprint
- Edge or toolkit builds listed in: Qualcomm AI Hub.
- 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.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelMobileSAMKyung Hee University, vision
MobileSAMKyung Hee University, visionR&D TopicsPromptable Segmentation Foundation Models (Segment Anything)Efficient Vision Networks for Mobile and Edge Devices
Use CasesMedical Image SegmentationHealthcareUse 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
R&D topics 2
Efficient Vision Networks for Mobile and Edge DevicesSmall, fast vision networks, often found by architecture search, that run on phones, came…produced byPromptable Segmentation Foundation Models (Segment Anything)Models that cut out any object from a point, box or text prompt, trained on very large ma…exemplar
Sources
- arxiv.org/abs/2306.14289 https://arxiv.org/abs/2306.14289
- aihub.qualcomm.com/models/mobilesam https://aihub.qualcomm.com/models/mobilesam
- github.com/facebookresearch/segment-anything https://github.com/facebookresearch/segment-anything
- modelscope.cn/models/PAI/MobileSAM https://www.modelscope.cn/models/PAI/MobileSAM
- docs.ultralytics.com/models/mobile-sam https://docs.ultralytics.com/models/mobile-sam/
- arxiv.org/html/2306.14289 https://arxiv.org/html/2306.14289
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MobileSAM", https://aurion.semai.id/models/mobilesam/, records of October 2026.