x64arm64 at 2 vCPU4 vCPU8 vCPU
Real buildstime and cost per buildlower is betterarm64 · 8 vCPU
Rust cold build of spotify-player: cargo test and clippy
RunsOn is the cheapest; RunsOn tmpfs is the best value; Avrea is the fastest.
- RunsOntmpfs m9g.2xlarge · 32 GB 1m 27s $0.0043
- RunsOn m9g.2xlarge · EBS gp3 · 32 GB 1m 27s $0.0042
- Avrea 32 GB 1m 07s $0.0536
- Warpbuild 32 GB 2m 13s $0.0266
- Ubicloud standard · 32 GB 4m 04s $0.0203
- Blacksmith 32 GB 2m 55s $0.0292
- Namespace 8x16 · 16 GB 4m 08s $0.0496
- WarpbuildApple silicon 12 vCPU · xfast (Apple M4 Pro) · 28 GB 1m 10s $0.1867
- AWS CodeBuild no arm64 runner
- boat no arm64 runner
- GitHub no 8 vCPU arm64 runner
- NamespaceApple silicon no 8 vCPU arm64 runner
TypeScript cold bun install and typecheck of opencode
RunsOn tmpfs is the best value and the cheapest; Avrea is the fastest.
- RunsOntmpfs m9g.2xlarge · 32 GB 46s $0.0025
- RunsOn m9gd.2xlarge · local NVMe · 32 GB 44s $0.0030
- Warpbuild 32 GB 1m 03s $0.0126
- Ubicloud standard · 32 GB 1m 51s $0.0092
- Blacksmith 32 GB 1m 26s $0.0143
- Namespace 8x16 · 16 GB 2m 03s $0.0246
- Avrea 32 GB 40s $0.0320
- WarpbuildApple silicon 12 vCPU · xfast (Apple M4 Pro) · 28 GB 47s $0.1240
- AWS CodeBuild no arm64 runner
- boat no arm64 runner
- GitHub no 8 vCPU arm64 runner
- NamespaceApple silicon no 8 vCPU arm64 runner
Docker PostHog's production image, built cold with buildx
RunsOn is the best value; RunsOn tmpfs is the cheapest; Avrea is the fastest.
- RunsOn m9gd.2xlarge · local NVMe · 32 GB 4m 51s $0.0167
- RunsOntmpfs m9g.2xlarge · 32 GB 4m 29s $0.0117
- Warpbuild 32 GB 6m 58s $0.0836
- Blacksmith 32 GB 7m 39s $0.0765
- Ubicloud standard · 32 GB 12m 12s $0.0610
- Avrea 32 GB 3m 57s $0.1896
- Namespace 8x16 · 16 GB 10m 57s $0.1314
- WarpbuildApple silicon 12 vCPU · xfast (Apple M4 Pro) · 28 GB 5m 59s $0.9573
- AWS CodeBuild no arm64 runner
- boat no arm64 runner
- GitHub no 8 vCPU arm64 runner
- NamespaceApple silicon no 8 vCPU 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