mit-han-lab/tinyml

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1211 stars · 168 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MIT Han Lab's TinyML research repository containing projects like TinyTL and NetAug for memory-efficient deep learning on microcontrollers and IoT devices. It hosts code for on-device learning and training techniques for tiny neural networks, with MCUNet refactored into a standalone repo.

Use cases

• run deep learning inference on microcontrollers
• train tiny neural networks for IoT devices
• memory-efficient transfer learning on edge devices
• deploy AI models on resource-constrained hardware
• augment training of small neural networks
• fit deep learning models into limited MCU memory

When to choose

• you need memory-efficient deep learning on microcontrollers or IoT devices
• you want on-device transfer learning with minimal RAM
• you're researching efficient tiny neural network training techniques

When to avoid

• you need general-purpose deep learning on servers or GPUs
• you want actively maintained code - MCUNet moved to a standalone repo
• you need production-ready deployment tooling rather than research code

Facets

library · maturity maintenance

machine-learning deep-learning llm-training machine-learning iot embedded-systems computer-vision python embedded iot tinyml microcontrollers model-efficiency on-device-learning research-code nasa-han-lab

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mit-han-lab/tinyml")