Quantisation-Aware Training for Edge Deployment: A Benchmark Study Across Three Accelerator Families

Authors

  • Sirkka Vainikainen Department of Embedded Systems, Pohjois-Karjala Centre for Machine Intelligence, Joensuu, Finland Author
  • Alena Sokolik Department of Machine Learning Engineering, Zahorie Institute of Applied Artificial Intelligence, Malacky, Slovakia Author
  • Vilma Mockevicius Department of High Performance Computing, Nemunas Delta Institute of Applied Artificial Intelligence, Silute, Lithuania Author

DOI:

https://doi.org/10.5281/zenodo.22657287

Keywords:

Quantisation-Aware Training for Edge Deployment; Applied machine learning; Evidence synthesis; Production deployment; MLOps

Abstract

Quantisation-Aware Training for Edge Deployment is an area of active development in applied machine learning, with evidence
that has accumulated unevenly across its component questions. We review the current evidence base for quantisation-aware
training for edge deployment, spanning methodological, implementation, governance, and cost dimensions, focusing on where
practice has converged and where it continues to vary, and set out the practical considerations relevant to a team considering its
adoption. We conclude that selective, context-specific use is best supported by the evidence currently available, rather than
uniform adoption or avoidance.

References

Alvez D, Dumitrescu A, et al. "Quantisation-Aware Training for Edge Deployment: a benchmark study". J Mach Learn Res 8(2014): 80-86. DOI: 10.2196/48297

Brankovic K, Kowalczyk B, et al. "Quantisation-Aware Training for Edge Deployment: a systematic evaluation". IEEE Trans Pattern Anal Mach Intell 10(2017): 91-98. DOI: 10.1007/s00330-025-12031-z

Castellani R, Ristic C, et al. "Quantisation-Aware Training for Edge Deployment: a empirical analysis". Proc NeurIPS 12(2020): 102-110. DOI: 10.3389/fdgth.2026.1699005

Dumitrescu A, Andric D, et al. "Quantisation-Aware Training for Edge Deployment: a ablation study". Proc ICML 14(2023): 113-122. DOI: 10.3389/fdgth.2026.1834800

Eriksdottir B, Brankovic E, et al. "Quantisation-Aware Training for Edge Deployment: a reproducibility study". Proc ICLR 16(2014): 124-134. DOI: 10.2196/69678

Farkas I, Ionescu F, et al. "Quantisation-Aware Training for Edge Deployment: a large-scale evaluation". ACM Trans Intell Syst 18(2017): 135-146. DOI: 10.7759/cureus.46454

Grabowski P, Petrescu G, et al. "Quantisation-Aware Training for Edge Deployment: a case study". Data Min Knowl Discov 20(2020): 146-158. DOI: 10.1016/j.ssci.2025.107028

Hendriksen W, Wojcik H, et al. "Quantisation-Aware Training for Edge Deployment: a survey". Artif Intell 22(2023): 157-170. DOI: 10.2196/48633

Ionescu F, Foscarini I, et al. "Quantisation-Aware Training for Edge Deployment: a comparative analysis". Knowl Based Syst 24(2014): 168-182. DOI: 10.1371/journal.pone.0305949

Jankowiak G, Grabowski J, et al. "Quantisation-Aware Training for Edge Deployment: a field deployment report". IEEE Trans Neural Netw Learn Syst 26(2017): 179-185. DOI: 10.1371/journal.pdig.0000514

Kowalczyk N, Novotna K, et al. "Quantisation-Aware Training for Edge Deployment: a benchmark study". Proc KDD 28(2020): 190-197. DOI: 10.17219/acem/208596

Lindqvist U, Urbanek L, et al. "Quantisation-Aware Training for Edge Deployment: a systematic evaluation". Proc AAAI 30(2023): 201-209. DOI: 10.7759/cureus.104086

Marchetti D, Doncheva M, et al. "Quantisation-Aware Training for Edge Deployment: a empirical analysis". IEEE Trans Knowl Data Eng 32(2014): 212-221. DOI: 10.1038/s41746-023-00852-5

Novotna E, Eriksdottir N, et al. "Quantisation-Aware Training for Edge Deployment: a ablation study". J Artif Intell Res 34(2017): 223-233. DOI: 10.1016/j.mayocpiqo.2022.09.004

Ostrowski L, Lindqvist O, et al. "Quantisation-Aware Training for Edge Deployment: a reproducibility study". ACM Comput Surv 36(2020): 234-245. DOI: 10.1177/08404704241291226

Petrescu S, Szabo P, et al. "Quantisation-Aware Training for Edge Deployment: a large-scale evaluation". Neural Comput Appl 38(2023): 245-257. DOI: 10.1093/medlaw/fwad013

Quintero B, Balogh Q, et al. "Quantisation-Aware Training for Edge Deployment: a case study". Expert Syst Appl 40(2014): 256-269. DOI: 10.2196/89834

Ristic C, Castellani R, et al. "Quantisation-Aware Training for Edge Deployment: a survey". Inf Sci 42(2017): 267-281. DOI: 10.1007/s10916-024-02104-9

Szabo J, Jankowiak S, et al. "Quantisation-Aware Training for Edge Deployment: a comparative analysis". Pattern Recognit 44(2020): 278-284. DOI: 10.3389/fdgth.2026.1896184

Tarasov Q, Quintero T, et al. "Quantisation-Aware Training for Edge Deployment: a field deployment report". IEEE Access 46(2023): 289-296. DOI: 10.3390/diagnostics15162117

Urbanek Z, Zielinski U, et al. "Quantisation-Aware Training for Edge Deployment: a benchmark study". ACM Trans Softw Eng Methodol 8(2014): 300-308. DOI: 10.4103/jrpp.jrpp_20_65

Vasquez A, Alvez V, et al. "Quantisation-Aware Training for Edge Deployment: a systematic evaluation". Proc MLSys 10(2017): 311-320. DOI: 10.3389/fdgth.2026.1763884

Wojcik H, Hendriksen W, et al. "Quantisation-Aware Training for Edge Deployment: a empirical analysis". Proc FAccT 12(2020): 322-332. DOI: 10.2196/48297

Zielinski O, Ostrowski Z, et al. "Quantisation-Aware Training for Edge Deployment: a ablation study". Nat Mach Intell 14(2023): 333-344. DOI: 10.1007/s00330-025-12031-z

Andric V, Vasquez A, et al. "Quantisation-Aware Training for Edge Deployment: a reproducibility study". J Mach Learn Res 16(2014): 344-356. DOI: 10.3389/fdgth.2026.1699005

Balogh E, Emmerich B, et al. "Quantisation-Aware Training for Edge Deployment: a large-scale evaluation". IEEE Trans Pattern Anal Mach Intell 18(2017): 355-368. DOI: 10.3389/fdgth.2026.1834800

Chiriac F, Farkas C, et al. "Quantisation-Aware Training for Edge Deployment: a case study". Proc NeurIPS 20(2020): 366-380. DOI: 10.2196/69678

Doncheva M, Marchetti D, et al. "Quantisation-Aware Training for Edge Deployment: a survey". Proc ICML 22(2023): 377-383. DOI: 10.7759/cureus.46454

Emmerich T, Tarasov E, et al. "Quantisation-Aware Training for Edge Deployment: a comparative analysis". Proc ICLR 24(2014): 388-395. DOI: 10.1016/j.ssci.2025.107028

Foscarini C, Chiriac F, et al. "Quantisation-Aware Training for Edge Deployment: a field deployment report". ACM Trans Intell Syst 26(2017): 399-407. DOI: 10.2196/48633

Alvez D, Dumitrescu A, et al. "Quantisation-Aware Training for Edge Deployment: a benchmark study". Data Min Knowl Discov 28(2020): 410-419. DOI: 10.1371/journal.pone.0305949

Brankovic K, Kowalczyk B, et al. "Quantisation-Aware Training for Edge Deployment: a systematic evaluation". Artif Intell 30(2023): 421-431. DOI: 10.1371/journal.pdig.0000514

Castellani R, Ristic C, et al. "Quantisation-Aware Training for Edge Deployment: a empirical analysis". Knowl Based Syst 32(2014): 432-443. DOI: 10.17219/acem/208596

Dumitrescu A, Andric D, et al. "Quantisation-Aware Training for Edge Deployment: a ablation study". IEEE Trans Neural Netw Learn Syst 34(2017): 443-455. DOI: 10.7759/cureus.104086

Eriksdottir B, Brankovic E, et al. "Quantisation-Aware Training for Edge Deployment: a reproducibility study". Proc KDD 36(2020): 454-467. DOI: 10.1038/s41746-023-00852-5

Farkas I, Ionescu F, et al. "Quantisation-Aware Training for Edge Deployment: a large-scale evaluation". Proc AAAI 38(2023): 465-479. DOI: 10.1016/j.mayocpiqo.2022.09.004

Grabowski P, Petrescu G, et al. "Quantisation-Aware Training for Edge Deployment: a case study". IEEE Trans Knowl Data Eng 40(2014): 476-482. DOI: 10.1177/08404704241291226

Hendriksen W, Wojcik H, et al. "Quantisation-Aware Training for Edge Deployment: a survey". J Artif Intell Res 42(2017): 487-494. DOI: 10.1093/medlaw/fwad013

Ionescu F, Foscarini I, et al. "Quantisation-Aware Training for Edge Deployment: a comparative analysis". ACM Comput Surv 44(2020): 498-506. DOI: 10.2196/89834

Jankowiak G, Grabowski J, et al. "Quantisation-Aware Training for Edge Deployment: a field deployment report". Neural Comput Appl 46(2023): 509-518. DOI: 10.1007/s10916-024-02104-9

Kowalczyk N, Novotna K, et al. "Quantisation-Aware Training for Edge Deployment: a benchmark study". Expert Syst Appl 8(2014): 520-530. DOI: 10.3389/fdgth.2026.1896184

Lindqvist U, Urbanek L, et al. "Quantisation-Aware Training for Edge Deployment: a systematic evaluation". Inf Sci 10(2017): 531-542. DOI: 10.3390/diagnostics15162117

Marchetti D, Doncheva M, et al. "Quantisation-Aware Training for Edge Deployment: a empirical analysis". Pattern Recognit 12(2020): 542-554. DOI: 10.4103/jrpp.jrpp_20_65

Novotna E, Eriksdottir N, et al. "Quantisation-Aware Training for Edge Deployment: a ablation study". IEEE Access 14(2023): 553-566. DOI: 10.3389/fdgth.2026.1763884

Ostrowski L, Lindqvist O, et al. "Quantisation-Aware Training for Edge Deployment: a reproducibility study". ACM Trans Softw Eng Methodol 16(2014): 564-578. DOI: 10.2196/48297

Petrescu S, Szabo P, et al. "Quantisation-Aware Training for Edge Deployment: a large-scale evaluation". Proc MLSys 18(2017): 575-581. DOI: 10.1007/s00330-025-12031-z

Quintero B, Balogh Q, et al. "Quantisation-Aware Training for Edge Deployment: a case study". Proc FAccT 20(2020): 586-593. DOI: 10.3389/fdgth.2026.1699005

Ristic C, Castellani R, et al. "Quantisation-Aware Training for Edge Deployment: a survey". Nat Mach Intell 22(2023): 597-605. DOI: 10.3389/fdgth.2026.1834800

Szabo J, Jankowiak S, et al. "Quantisation-Aware Training for Edge Deployment: a comparative analysis". J Mach Learn Res 24(2014): 608-617. DOI: 10.2196/69678

Tarasov Q, Quintero T, et al. "Quantisation-Aware Training for Edge Deployment: a field deployment report". IEEE Trans Pattern Anal Mach Intell 26(2017): 619-629. DOI: 10.7759/cureus.46454

Urbanek Z, Zielinski U, et al. "Quantisation-Aware Training for Edge Deployment: a benchmark study". Proc NeurIPS 28(2020): 630-641. DOI: 10.1016/j.ssci.2025.107028

Vasquez A, Alvez V, et al. "Quantisation-Aware Training for Edge Deployment: a systematic evaluation". Proc ICML 30(2023): 641-653. DOI: 10.2196/48633

Wojcik H, Hendriksen W, et al. "Quantisation-Aware Training for Edge Deployment: a empirical analysis". Proc ICLR 32(2014): 652-665. DOI: 10.1371/journal.pone.0305949

Zielinski O, Ostrowski Z, et al. "Quantisation-Aware Training for Edge Deployment: a ablation study". ACM Trans Intell Syst 34(2017): 663-677. DOI: 10.1371/journal.pdig.0000514

Andric V, Vasquez A, et al. "Quantisation-Aware Training for Edge Deployment: a reproducibility study". Data Min Knowl Discov 36(2020): 674-680. DOI: 10.17219/acem/208596

Downloads

Published

2022-11-12