mlsanityData to 7 Oct 2026

MLPerf Tiny Benchmark

arXiv 2106.07597 ↗First posted 14 Jun 2021cs.LG cs.ARcited by 118

Not on the map. Why?

Abstract (arXiv)

Advancements in ultra-low-power tiny machine learning (TinyML) systems promise to unlock an entirely new class of smart applications. However, continued progress is limited by the lack of a widely accepted and easily reproducible benchmark for these systems. To meet this need, we present MLPerf Tiny, the first industry-standard benchmark suite for ultra-low-power tiny machine learning systems. The benchmark suite is the collaborative effort of more than 50 organizations from industry and academia and reflects the needs of the community. MLPerf Tiny measures the accuracy, latency, and energy of machine learning inference to properly evaluate the tradeoffs between systems. Additionally, MLPerf Tiny implements a modular design that enables benchmark submitters to show the benefits of their product, regardless of where it falls on the ML deployment stack, in a fair and reproducible manner. The suite features four benchmarks: keyword spotting, visual wake words, image classification, and anomaly detection.

Key facts. Cited by 118 papers in the map (data through 7 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 14 Jun 2021.

Builds on

11 of 25 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  5. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 161
  6. 2017Hello Edge: Keyword Spotting on Microcontrollerscited by 108
  7. 2019MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspectioncited by 57
  8. 2019SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollerscited by 52
  9. 2019Visual Wake Words Datasetcited by 46
  10. 2019ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detectioncited by 43
  11. 2020Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoringcited by 43

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 20; 2023: 25; 2024: 13; 2025: 29; 2026: 30.

118 papers.

Sort:

By area:

  1. 2021Randomness In Neural Network Training: Characterizing The Impact of Toolingcited by 57
  2. 2025Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latencycited by 32
  3. 2022Machine Learning for Microcontroller-Class Hardware: A Reviewcited by 28
  4. 2024Differentiable Weightless Neural Networkscited by 27
  5. 2023A Machine Learning-oriented Survey on Tiny Machine Learningcited by 26
  6. 2022Edge Impulse: An MLOps Platform for Tiny Machine Learningcited by 24
  7. 2025TokenPowerBench: Benchmarking the Power Consumption of LLM Inferencecited by 21
  8. 2024MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AIcited by 15
  9. 2022XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaversecited by 14
  10. 2022Intelligence at the Extreme Edge: A Survey on Reformable TinyMLcited by 13
  11. 2024On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systemscited by 13
  12. 2025KANEL'E: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluationcited by 13
38 more
  1. 2022FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learningcited by 12
  2. 2022CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAscited by 11
  3. 2024Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollerscited by 11
  4. 2022UDC: Unified DNAS for Compressible TinyML Modelscited by 10
  5. 2023AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computingcited by 10
  6. 2022Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodescited by 9
  7. 2022Open-source FPGA-ML codesign for the MLPerf Tiny Benchmarkcited by 9
  8. 2023PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimizationcited by 9
  9. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9
  10. 2022Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflowscited by 8
  11. 2023Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devicescited by 7
  12. 2022An Empirical Study of Low Precision Quantization for TinyMLcited by 6
  13. 2023Tailor: Altering Skip Connections for Resource-Efficient Inferencecited by 6
  14. 2023Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyMLcited by 6
  15. 2024Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networkscited by 6
  16. 2025LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deploymentcited by 6
  17. 2022Machine Learning Sensorscited by 5
  18. 2022T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXitcited by 5
  19. 2022Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarkscited by 5
  20. 2023MLonMCU: TinyML Benchmarking with Fast Retargetingcited by 5
  21. 2023U-TOE: Universal TinyML On-board Evaluation Toolkit for Low-Power IoTcited by 5
  22. 2024On-device Online Learning and Semantic Management of TinyML Systemscited by 5
  23. 2025From Tiny Machine Learning to Tiny Deep Learning: A Surveycited by 5
  24. 2022Depth Pruning with Auxiliary Networks for TinyMLcited by 4
  25. 2023RedMule: A Mixed-Precision Matrix-Matrix Operation Engine for Flexible and Energy-Efficient On-Chip Linear Algebra and TinyML Training Accelerationcited by 4
  26. 2023Reaching the Edge of the Edge: Image Analysis in Spacecited by 4
  27. 2023Is TinyML Sustainable? Assessing the Environmental Impacts of Machine Learning on Microcontrollerscited by 4
  28. 2023TinyReptile: TinyML with Federated Meta-Learningcited by 4
  29. 2023The Case for Hierarchical Deep Learning Inference at the Network Edgecited by 4
  30. 2024QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoringcited by 4
  31. 2024xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systemscited by 4
  32. 2024TinyChirp: Bird Song Recognition Using TinyML Models on Low-power Wireless Acoustic Sensorscited by 4
  33. 2025Benchmarking Energy and Latency in TinyML: A Novel Method for Resource-Constrained AIcited by 4
  34. 2023Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networkscited by 3
  35. 2023Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inferencecited by 3
  36. 2025An All-digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification Acceleratorcited by 3
  37. 2025AI Benchmark Democratization and Carpentrycited by 3
  38. 2022Bit-serial Weight Pools: Compression and Arbitrary Precision Execution of Neural Networks on Resource Constrained Processorscited by 2

50 most cited of 118 All 118 (JSON)