x64arm64 at 2 vCPU4 vCPU8 vCPU
Real buildstime and cost per buildlower is betterarm64 · 4 vCPU
Rust cold build of spotify-player: cargo test and clippy
RunsOn is the best value and the cheapest; Namespace Apple silicon is the fastest.
- RunsOn m9g.xlarge · EBS gp3 · 16 GB 2m 01s $0.0036
- RunsOntmpfs m9g.xlarge · 16 GB 2m 05s $0.0037
- Avrea 16 GB 1m 27s $0.0348
- Warpbuild 16 GB 3m 14s $0.0194
- GitHub 16 GB 3m 18s $0.0264
- Ubicloud standard · 16 GB 6m 07s $0.0153
- Blacksmith 16 GB 4m 13s $0.0211
- NamespaceApple silicon 4x16 · 16 GB 1m 25s $0.1190
- Namespace 4x8 · 8 GB 5m 51s $0.0351
- WarpbuildApple silicon 6 vCPU · xfast (Apple M4 Pro) · 14 GB 1m 28s $0.1173
- AWS CodeBuild no arm64 runner
- boat no arm64 runner
TypeScript cold bun install and typecheck of opencode
RunsOn is the best value and the cheapest; Namespace Apple silicon is the fastest.
- RunsOn m9gd.xlarge · local NVMe · 16 GB 1m 03s $0.0018
- RunsOntmpfs m9g.xlarge · 16 GB 1m 04s $0.0022
- Warpbuild 16 GB 1m 37s $0.0097
- GitHub 16 GB 1m 44s $0.0139
- Blacksmith 16 GB 2m 14s $0.0111
- Avrea 16 GB 49s $0.0196
- Namespace 4x16 · 16 GB 3m 24s $0.0407
- NamespaceApple silicon 4x16 · 16 GB 49s $0.0679
- Ubicloud standard · 16 GB 2m 44s $0.0068
- WarpbuildApple silicon 6 vCPU · xfast (Apple M4 Pro) · 14 GB 58s $0.0767
- AWS CodeBuild no arm64 runner
- boat no arm64 runner
Docker PostHog's production image, built cold with buildx
RunsOn is the best value and the cheapest; Avrea is the fastest.
- RunsOn m9gd.xlarge · local NVMe · 16 GB 6m 48s $0.0099
- RunsOntmpfs r9g.xlarge · 32 GB 5m 40s $0.0139
- Ubicloud standard · 16 GB 15m 51s $0.0396
- Avrea 16 GB 5m 07s $0.1228
- Blacksmith 16 GB 11m 00s $0.0550
- Warpbuild 16 GB 10m 57s $0.0657
- GitHub 16 GB 11m 28s $0.0917
- Namespace 4x16 · 16 GB 14m 18s $0.1716
- NamespaceApple silicon 4x16 · 16 GB 5m 23s $0.4522
- WarpbuildApple silicon 6 vCPU · xfast (Apple M4 Pro) · 14 GB 7m 08s $0.5707
- AWS CodeBuild no arm64 runner
- boat no arm64 runner
Each row's best-value machine of this size for that build (lowest time × cost, ranked on p90), in that order, named under the provider. Time is the median whole job, cost is that job at the provider's per-minute price (RunsOn at EC2 spot). Yellow marks the fastest and the cheapest. Apple silicon and tmpfs (workspace in RAM) machines are rows of their own; a faded row is provisional or a machine of another size, and takes no place. A row that did not finish a build stays listed with the reason.
Full build benchmark every phase, p90 and worst runs, queue under a burst, run-to-run spread, bigger runners