quickstart →

RunsOn c8g.xlarge · EBS gp3 vs Blacksmith 4 vCPU arm64

RunsOn does the Rust and TypeScript builds for 3.3–4.4× less and 1.5–1.6× faster. Both 4 vCPU arm64.

Price per minute 3.1× cheaper on RunsOn: $0.0016 vs $0.0050the builds are not all compared on cost yet
Rust build 4.4× cheaper on RunsOn: $0.0048 vs $0.0210RunsOn 1.6× faster: 2m 29s vs 3m 59s
TypeScript build 3.3× cheaper on RunsOn: $0.0033 vs $0.0111RunsOn 1.5× faster: 1m 19s vs 1m 55s
Docker build 10m 32s Blacksmith only · RunsOn not run

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 Blacksmith Gap
Cost
Cost per Rust build $0.0048 $0.0210 4.4× RunsOn
Cost per TypeScript build $0.0033 $0.0111 3.3× RunsOn
Cost per Docker build n/a: Not run: the PostHog Docker build needs more than 8 GB of memory; it ran out of memory on 8 GB runners. $0.0555 —
Price per minute $0.0016 $0.0050 3.1× RunsOn
Real builds, wall time
Rust build (spotify-⁠player) 2m 29s 3m 59s 1.6× RunsOn
TypeScript build (opencode) 1m 19s 1m 55s 1.5× RunsOn
Docker build (PostHog) n/a: Not run: the PostHog Docker build needs more than 8 GB of memory; it ran out of memory on 8 GB runners. 10m 32s —
CPU & memory
PassMark single-⁠thread (points) 1,947 1,353 1.4× RunsOn
PassMark CPU Mark, all cores (points) 3,935 3,783 ≈ even
sysbench CPU, 1 thread (events/s) 3,174 929 3.4× RunsOn
7-⁠Zip compression (MIPS) 31,897 17,447 1.8× RunsOn
Memory read bandwidth 19.2 GiB/s 9.0 GiB/s 2.1× RunsOn
Measurement RunsOn Blacksmith Gap
Workspace disk (fio)
Random read, 4k QD32 (IOPS) 2,992 253,175 84.6× Blacksmith
Random write, 4k QD32 (IOPS) 2,994 35,622 11.9× Blacksmith
Random read, 4k QD1 (IOPS) 1,803 32,740 18.2× Blacksmith
QD1 read latency, p99 860 µs 37 µs 23.5× Blacksmith
Sequential read 401 MiB/s 1.7 GiB/s 4.2× Blacksmith
Sequential write 401 MiB/s 829 MiB/s 2.1× Blacksmith
Sync write, 4k + fdatasync (IOPS) 538 9,366 17.4× Blacksmith
Network, cache & Docker
Download from GitHub 199 MiB/s 100 MiB/s 2.0× RunsOn
Cache restore, 4 GB (actions/cache) 19s 21s 1.1× RunsOn
Cache save, 4 GB (actions/cache) 14s 14s ≈ even
docker pull 5.8s 12.9s 2.2× RunsOn
Database
pgbench read/write (TPS) 2,660 2,948 1.1× Blacksmith
pgbench read-⁠only (TPS) 40,425 24,073 1.7× RunsOn
Queue
Queue under burst load 17s 12s 1.4× Blacksmith
  • ≈ even: under 5% apart, or a build inside both runners' run-to-run spread
  • Queue: identical jobs queued at the same instant (burst suite)
  • 2 missing on one side or both
  • RunsOn at EC2 spot, its default (7-day average of the cheapest us-east-1 zone's spot price, fetched 16 Nov 2026); 3 of its jobs fell back to on-demand (AWS had no spot capacity for the type) and are priced at the spot rate over the same billed time
  • Cost: a managed SaaS runner against RunsOn self-hosted on your AWS account; the effort of running it was not measured

Other head-to-heads