TinyMLfamily
MCUNet
MIT Han Lab system for running neural networks on microcontrollers; last dated news Mar 2024 (low activity).
Levelfamily
ClassTinyML
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessopen source
Runs onmicrocontroller
Statusactive
Benchmark Results
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
mcunet-in4 belongs to this familyTinyMLmcunet-vww2 belongs to this familyTinyMLWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
R&D Topics
Runtimes
Identity
- Developer
- MIT Han Lab
- Family
- not in the notes
- Released
- – sources
- 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
- CNN TinyNAS neural architecture search co-designed with TinyEngine inference engine
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text
- Output
- labels and boxes
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 source
- Licence
- MIT License sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- microcontroller
- Footprint
- ImageNet models: SRAM 242 to 456 kB, Flash 878 to 1876 kB; profiled on STM32F746
- Runtimes
- TinyEngine (MCUNet)
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
DeveloperMIT Han Labuniversity, USA
MIT Han Labuniversity, USAModelMCUNetMIT Han Lab, TinyML
MCUNetMIT Han Lab, TinyMLR&D TopicsTinyML on Microcontrollers
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- GitHub - mit-han-lab/mcunet: [NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based github.com https://github.com/mit-han-lab/mcunet
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MCUNet", https://aurion.semai.id/models/mit-han-lab-mcunet/, records of October 2026.