Blacksmith 4 vCPU x64 vs Namespace 4x16 x64
Blacksmith does each build for 1.2–1.4× less; the two take about the same time. Both 4 vCPU x64.
All three builds 1.3× cheaper on Blacksmith: $0.0728 vs $0.0966Namespace 1.1× faster: 7m 26s vs 8m 12s
Rust build 1.2× cheaper on Blacksmith: $0.0175 vs $0.0208about the same time: 1m 59s · 1m 38s
TypeScript build 1.2× cheaper on Blacksmith: $0.0089 vs $0.0108about the same time: 54s · 47s
Docker build 1.4× cheaper on Blacksmith: $0.0464 vs $0.0650about the same time: 5m 19s · 5m 01s
Blacksmith 4 vCPU
jobs ran from Secured Servers (US)
Namespace 4x16
jobs ran from Namespace Labs (US)
Side by side
Every measurement both runners share, cost first. The dot marks the better value; gap is the larger over the smaller.
| Measurement | Blacksmith | Namespace | Gap |
|---|---|---|---|
| Cost | |||
| Cost per Rust build | $0.0175 | $0.0208 | 1.2× Blacksmith |
| Cost per TypeScript build | $0.0089 | $0.0108 | 1.2× Blacksmith |
| Cost per Docker build | $0.0464 | $0.0650 | 1.4× Blacksmith |
| Price per minute | $0.0080 | $0.0120 overage rate | 1.5× Blacksmith |
| Real builds, wall time | |||
| Rust build (spotify-player) | 1m 59s | 1m 38s | ≈ even |
| TypeScript build (opencode) | 54s | 47s | ≈ even |
| Docker build (PostHog) | 5m 19s | 5m 01s | ≈ even |
| CPU & memory | |||
| PassMark single-thread (points) | 4,236 | 4,700 | 1.1× Namespace |
| PassMark CPU Mark, all cores (points) | 15,036 | 16,176 | 1.1× Namespace |
| sysbench CPU, 1 thread (events/s) | 6,419 | 7,051 | 1.1× Namespace |
| 7-Zip compression (MIPS) | 27,863 | 33,428 | 1.2× Namespace |
| Memory read bandwidth | 31.5 GiB/s | 44.8 GiB/s | 1.4× Namespace |
| Measurement | Blacksmith | Namespace | Gap |
|---|---|---|---|
| Workspace disk (fio) | |||
| Random read, 4k QD32 (IOPS) | 873,112 | 1,011,926 | 1.2× Namespace |
| Random write, 4k QD32 (IOPS) | 251,762 | 436,056 | 1.7× Namespace |
| Random read, 4k QD1 (IOPS) | 84,854 | 78,615 | 1.1× Blacksmith |
| QD1 read latency, p99 | 14 µs | 12 µs | 1.2× Namespace |
| Sequential read | 6.9 GiB/s | 4.1 GiB/s | 1.7× Blacksmith |
| Sequential write | 1.6 GiB/s | 2.9 GiB/s | 1.8× Namespace |
| Sync write, 4k + fdatasync (IOPS) | 18,024 | 17,844 | ≈ even |
| Network, cache & Docker | |||
| Download from GitHub | 107 MiB/s | 202 MiB/s | 1.9× Namespace |
| Cache restore, 4 GB (actions/cache) | 14s | 28s | 2.0× Blacksmith |
| Cache save, 4 GB (actions/cache) | 8s | 14s | 1.8× Blacksmith |
| docker pull | 6.5s | 4.2s | 1.6× Namespace |
| Database | |||
| pgbench read/write (TPS) | 11,775 | 8,463 | 1.4× Blacksmith |
| pgbench read-only (TPS) | 89,914 | 67,294 | 1.3× Blacksmith |
| Queue | |||
| Queue under burst load | 11s | 2m 23s plan limit | — |
- ≈ even: under 5% apart, or a build inside both runners' run-to-run spread
- Queue: identical jobs queued at the same instant (burst suite)
- Queue: not compared. Namespace's burst ran 4 jobs at a time, the concurrency limit of the plan this benchmark account is on