x64arm64 at 2 vCPU4 vCPU8 vCPU
docker pullsecondslower is betterarm64 · 4 vCPU
RunsOn tmpfs and Namespace Apple silicon tie for the fastest docker pull.
RunsOn tmpfs to Ubicloud: 4.0× apart.
- RunsOntmpfs median of 2 machines 4.5s
- NamespaceApple silicon 4x16 · 16 GB 4.7s
- RunsOn median of 3 machines 4.9s
- Avrea 16 GB 5.5s
- Warpbuild 16 GB 8.7s
- Blacksmith 16 GB 12.9s
- Namespace median of 2 machines 14.1s
- GitHub 16 GB 15.6s
- Ubicloud standard · 16 GB 18.1s
- WarpbuildApple silicon 6 vCPU · xfast (Apple M4 Pro) · 14 GB 8.6s not ranked
- AWS CodeBuild no arm64 runner
- boat no arm64 runner
The same image pulled on every runner, registry to disk: the download, then the layers unpacked, so the disk and the CPU count too.