# Benchmarking Ultra-Low-Power -NPUs

*2026-08-01 — paper*

Authors: Josh Millar, Yushan Huang, Sarab Sethi, Hamed Haddadi, Anil Madhavapeddy


Microcontrollers (MCUs) are widely used in resource-constrained environments
due to their form factor and low cost and power consumption. Performing model
inference on MCU-scale hardware improves privacy by running locally, lowers
operating costs for model vendors, and eliminates dependence on network
connectivity.

However, deployments remain constrained by limited memory,
throughput, and compute. The growing computational demands of modern models
have catalyzed specialized accelerators across the computing spectrum, from
data centers to embedded systems.

At this resource-constrained end, MCU-scale neural processing units, or NPUs,
have emerged to provide real-time or near-real-time inference within
milliwatt-scale power budgets.

See also the full paper at [Benchmarking Ultra-Low-Power μNPUs](https://anil.recoil.org/papers/2025-npu-bench)


DOI: 10.1145/3833428.3833430
Classification: full
Venue: GetMobile: Mobile Computing and Communications
Volume: 30
Issue: 2
URL: https://dl.acm.org/doi/10.1145/3833428.3833430

## Related

- [GetMOBILE article on benchmarking micro-NPUs now out](https://anil.recoil.org/notes/sigmobile-npu) (note, 2026-08-05)
- [Benchmarking Ultra-Low-Power μNPUs](https://anil.recoil.org/papers/2025-npu-bench) (paper, 2025-11-01)

---
Canonical: https://anil.recoil.org/papers/2026-benchmarking-npus
Type: paper
Tags: journal