RunsOn m8azn.xlarge · EBS gp3 vs Namespace 4x16 x64
RunsOn does each build for 2.0–3.2× less; neither is clearly faster (within 5% or inside each other's run-to-run range). Both 4 vCPU x64.
All three builds 2.2× cheaper on RunsOn: $0.0401 vs $0.0900Namespace 1.6× faster: 7m 02s vs 11m 26s
Rust build 3.2× cheaper on RunsOn: $0.0061 vs $0.0198within run-to-run spread: 1m 42s · 1m 33s
TypeScript build 2.6× cheaper on RunsOn: $0.0041 vs $0.0106within run-to-run spread: 57s · 45s
Docker build 2.0× cheaper on RunsOn: $0.0298 vs $0.0596within run-to-run spread: 8m 48s · 4m 44s
RunsOn m8azn.xlarge · EBS gp3
jobs ran from Amazon.com (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 | RunsOn | Namespace | Gap |
|---|---|---|---|
| Cost | |||
| Cost per Rust build | $0.0061 | $0.0198 | 3.2× RunsOn |
| Cost per TypeScript build | $0.0041 | $0.0106 | 2.6× RunsOn |
| Cost per Docker build | $0.0298 | $0.0596 | 2.0× RunsOn |
| Price per minute | $0.0024 | $0.0120 overage rate | 5.1× RunsOn |
| Real builds, wall time | |||
| Rust build (spotify-player) | 1m 42s | 1m 33s | ≈ even |
| TypeScript build (opencode) | 57s | 45s | ≈ even |
| Docker build (PostHog) | 8m 48s | 4m 44s | ≈ even |
| CPU & memory | |||
| PassMark single-thread (points) | 4,267 | 4,628 | 1.1× Namespace |
| PassMark CPU Mark, all cores (points) | 15,136 | 15,965 | 1.1× Namespace |
| sysbench CPU, 1 thread (events/s) | 5,617 | 6,887 | 1.2× Namespace |
| 7-Zip compression (MIPS) | 42,512 | 33,572 | 1.3× RunsOn |
| Memory read bandwidth | 40.9 GiB/s | 44.7 GiB/s | 1.1× Namespace |
| Measurement | RunsOn | Namespace | Gap |
|---|---|---|---|
| Workspace disk (fio) | |||
| Random read, 4k QD32 (IOPS) | 2,994 | 1,202,685 | 401.7× Namespace |
| Random write, 4k QD32 (IOPS) | 2,992 | 564,373 | 188.7× Namespace |
| Random read, 4k QD1 (IOPS) | 1,583 | 104,443 | 66.0× Namespace |
| QD1 read latency, p99 | 918 µs | 11 µs | 85.0× Namespace |
| Sequential read | 401 MiB/s | 5.0 GiB/s | 12.7× Namespace |
| Sequential write | 401 MiB/s | 3.4 GiB/s | 8.6× Namespace |
| Sync write, 4k + fdatasync (IOPS) | 541 | 28,561 | 52.8× Namespace |
| Network, cache & Docker | |||
| Download from GitHub | 267 MiB/s | 187 MiB/s | 1.4× RunsOn |
| Cache restore, 4 GB (actions/cache) | 16s | 21s | 1.3× RunsOn |
| Cache save, 4 GB (actions/cache) | 16s | 13s | 1.2× Namespace |
| docker pull | 4.6s | 3.2s | 1.4× Namespace |
| Database | |||
| pgbench read/write (TPS) | 3,326 | 13,662 | 4.1× Namespace |
| pgbench read-only (TPS) | 162,964 | 114,631 | 1.4× RunsOn |
| Queue | |||
| Queue under burst load | 17s | 10s | 1.7× Namespace |
- ≈ even: under 5% apart, or a build inside both runners' run-to-run spread
- Queue: identical jobs queued at the same instant (burst suite)
- RunsOn at EC2 spot, its default (7-day average of the cheapest us-east-1 zone's spot price, fetched 16 Nov 2026); its jobs ran on spot
- Cost: a managed SaaS runner against RunsOn self-hosted on your AWS account; the effort of running it was not measured