Skip to main content

CubePath rz.starter

Miami

Benchmark complete
Finished Oct 15, 2026
Geekbench 7 single-core
2,193
Faster than 96% of 2 vCPU plans
Geekbench 7 multi-core
4,088
Faster than 100% of 2 vCPU plans
Disk 4K IOPS
10,304
fio random read and write, 50/50
Monthly price at test time
$16.22
252 multi-core points per dollar
Same price today

Server

  • Provider
    CubePath
  • Plan
    rz.starter
  • Location
    Miami
  • vCPU
    2
  • RAM
    4 GB
  • Storage
    80 GB NVMe
  • Network
    Unknown
  • OS image
    ubuntu-24
  • Trigger
    Scheduled
  • Queued at
    Oct 15, 2026, 07:30:00 UTC
Visit CubePath

Latest runs of this plan

Full history of this plan

CPU

Version Single-core Multi-core
Geekbench 7 2,193 4,088 Geekbench Browser

Scores from different Geekbench versions aren't comparable with each other. Charts only use Geekbench 7.

Geekbench 7 workloads

Workload Single-core Multi-core
File Compression
2,219
5th of 191
3,746
32nd of 135
Navigation
2,447
1st of 191
Single-core only
HTML5 Browser
2,240
5th of 191
Single-core only
PDF Viewer
2,207
7th of 191
Single-core only
Photo Library
2,051
8th of 191
3,974
35th of 135
Clang
2,151
2nd of 191
4,450
35th of 135
Text Processing
2,003
6th of 191
3,849
38th of 135
Asset Compression
2,210
6th of 191
4,492
40th of 135
HDR
2,059
7th of 191
3,559
33rd of 135
Photo Editor
2,234
13th of 191
4,053
35th of 135
Ray Tracer
2,289
2nd of 191
4,717
35th of 135
Structure from Motion
2,289
7th of 191
Single-core only
Game Physics
2,387
2nd of 191
Single-core only
Video Encoder
2,163
6th of 191
Single-core only
Audio Encoder
2,176
6th of 191
Single-core only
Video Player
2,023
18th of 191
Single-core only

Rank among the 191 runs with Geekbench 7 workload scores. Bars are relative to the best run. Geekbench doesn't run every workload multi-core, so some rows only have a single-core score.

Memory, TLS and scheduler

Memory bandwidth (STREAM)

Test Result Runs Spread
Copy higher is better 44.7 GB/s 3 7.1%
Scale higher is better 37.7 GB/s 3 13.2%
Add higher is better 39.9 GB/s 3 20.7%
Triad higher is better 45.9 GB/s 3 20.2%

Average of 3 runs. Spread is the standard deviation as a share of the average.

TLS and crypto (OpenSSL)

Test Result Runs Spread
RSA 4096 signs higher is better 728/s 3 0.385%
RSA 4096 verifies higher is better 47,134/s 3 0.405%
SHA-256 higher is better 2.53 GB/s 3 9.14%
AES-256-GCM higher is better 12 GB/s 3 0.403%
ChaCha20-Poly1305 higher is better 6.72 GB/s 3 0.522%

Average of 3 runs. Spread is the standard deviation as a share of the average.

Scheduler latency (schbench)

Test Result Runs Spread
Request latency, median lower is better 2.84 ms 3 0.563%
Requests per second, 90th percentile higher is better 698/s 3 0.438%
Request latency, 99.9th percentile lower is better 5.11 ms 3 3.53%
Requests per second, average higher is better 692/s 3 0.374%

Average of 3 runs. Spread is the standard deviation as a share of the average.

Disk

Block size Read Write Total
4K 20.1 MB/s (5,150 IOPS) 20.1 MB/s (5,154 IOPS) 40.3 MB/s (10,304 IOPS)
64K 166.3 MB/s (2,660 IOPS) 167.1 MB/s (2,674 IOPS) 333.4 MB/s (5,334 IOPS)
512K 387.3 MB/s (774 IOPS) 407.9 MB/s (815 IOPS) 795.2 MB/s (1,589 IOPS)
1M 382.5 MB/s (382 IOPS) 408 MB/s (407 IOPS) 790.4 MB/s (789 IOPS)

fio random read and write, 50/50, run by YABS against the boot disk.

Network

IPv4 transfer speed

Loading...
Target Protocol Send Receive
Clouvider, London, UK (10G) IPv4 274 Mbps 926 Mbps
Eranium, Amsterdam, NL (100G) IPv4 198 Mbps 869 Mbps
Leaseweb, Singapore, SG (10G) IPv4 254 Mbps 836 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 371 Mbps 967 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 747 Mbps 987 Mbps

Public iperf3 servers vary in capacity and availability. Compare a target only with itself over time.

Datastores

PostgreSQL

fsync speed (pg_test_fsync)

Method Operations per second Time per operation
One 8 kB write
open_datasync 508 1.97 ms
fdatasync 437 2.29 ms
fsync 226 4.42 ms
fsync_writethrough Not supported here n/a
open_sync 230 4.34 ms
Two 8 kB writes
open_datasync 197 5.07 ms
fdatasync 475 2.1 ms
fsync 255 3.93 ms
fsync_writethrough Not supported here n/a
open_sync 117 8.57 ms
open_sync at different write sizes
1 * 16kB open_sync write 262 3.81 ms
2 * 8kB open_sync writes 134 7.46 ms
4 * 4kB open_sync writes 67.6 14.8 ms
8 * 2kB open_sync writes 28.8 34.7 ms
16 * 1kB open_sync writes 17.2 58.3 ms
fsync on a non-write descriptor
write, fsync, close 221 4.53 ms
write, close, fsync 277 3.61 ms
Non-synced 8 kB writes
write 1,030,182 0.001 ms

pg_test_fsync against the Docker volume Postgres keeps its data on. fdatasync is Linux's default wal_sync_method.

pgbench at scale 10

Workload Clients Transactions/s Median p95 p99 p99.9 Failed
Read/write (TPC-B like) 1 420 2.21 ms 3.23 ms 3.69 ms 8.02 ms 0
Read/write (TPC-B like) 8 1,245 5.23 ms 13.2 ms 19.5 ms 30.3 ms 0
Read/write (TPC-B like) 32 1,814 11.9 ms 52.8 ms 93.1 ms 159 ms 0
Read only 1 41,970 0.023 ms 0.03 ms 0.035 ms 0.056 ms 0
Read only 8 124,278 0.056 ms 0.088 ms 0.109 ms 0.176 ms 0
Read only 32 121,804 0.216 ms 0.311 ms 0.417 ms 0.781 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.14 s. 60 s per run, prepared statements. Latency comes from sampled transaction logs, and p99.9 is left out when fewer than 1,000 were sampled.

pgbench at scale 100

Workload Clients Transactions/s Median p95 p99 p99.9 Failed
Read/write (TPC-B like) 1 393 2.67 ms 3.25 ms 3.99 ms 13.3 ms 0
Read/write (TPC-B like) 8 1,532 4.96 ms 8.25 ms 23.7 ms 53.9 ms 0
Read/write (TPC-B like) 32 3,565 5.93 ms 24.5 ms 52.3 ms 112 ms 0
Read only 1 18,450 0.029 ms 0.047 ms 0.089 ms 0.533 ms 0
Read only 8 91,761 0.079 ms 0.126 ms 0.156 ms 0.506 ms 0
Read only 32 94,194 0.298 ms 0.442 ms 0.62 ms 1.29 ms 0

Scale 100 (10,000,000 accounts), loaded in 14.1 s. 60 s per run, prepared statements. Latency comes from sampled transaction logs, and p99.9 is left out when fewer than 1,000 were sampled.

MySQL

sysbench OLTP

Workload Threads Transactions/s Queries/s Median p95 p99 Errors
Read/write 1 110 2,209 8.74 ms 13.5 ms 20 ms 0
Read/write 8 380 7,609 20 ms 31.9 ms 48.3 ms 0
Read/write 32 1,060 21,190 28.7 ms 48.3 ms 66.8 ms 0
Read only 1 1,644 26,299 0.597 ms 0.702 ms 0.811 ms 0
Read only 8 3,786 60,582 2.07 ms 2.71 ms 3.13 ms 0
Read only 32 3,395 54,327 9.22 ms 11.4 ms 12.8 ms 0

10 tables of 100,000 rows, loaded in 13.4 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 118,985 108,168 0.319 ms 2.37 ms 3.1 ms
1:1 set:get 118,462 59,231 0.255 ms 2.38 ms 4.02 ms

1,000,000 keys of 32 bytes. 64 connections over 2 threads, 60 s per ratio.

Web frameworks

Framework Fortunes req/s Single query req/s JSON req/s Fortunes p99 at 256 connections
Next.js nextjs 1,249 4,371 6,065 310 ms
Express express-postgresjs 8,335 13,652 83,565 55.7 ms
Fastify fastify-postgres 8,060 13,856 85,119 55.5 ms
NestJS nestjs 9,526 10,502 42,462 50.6 ms
Nuxt nuxt 7,724 13,603 70,436 63.1 ms
FastAPI fastapi 7,025 8,823 44,172 146 ms
Django django-postgresql 3,413 3,801 9,721 130 ms
Rails rails 5,580 7,759 30,185 59.7 ms
Laravel laravel 1,540 1,625 3,015 173 ms
Symfony symfony 1,891 2,056 5,895 144 ms

Peak requests per second across the 64 and 256 connection levels, measured with wrk. Each test has to pass the TechEmpower response checks first, or it's marked invalid.

Web apps

WooCommerce

Page mix

Step Requests/s Median p95 p99 Error rate
8 virtual users
Home page 4.35 366 ms 434 ms 446 ms 0%
Shop page 4.35 494 ms 579 ms 590 ms 0%
Category page 4.35 319 ms 483 ms 558 ms 0%
Product page 4.35 354 ms 420 ms 438 ms 0%
Product search 4.35 304 ms 365 ms 379 ms 0%
32 virtual users
Home page 4.37 1.37 s 1.54 s 1.62 s 0%
Shop page 4.37 1.74 s 1.98 s 2.04 s 0%
Category page 4.37 1.54 s 1.83 s 1.95 s 0%
Product page 4.37 1.35 s 1.5 s 1.56 s 0%
Product search 4.37 1.27 s 1.4 s 1.45 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 8.2 403 ms 471 ms 487 ms 0%
Cart 8.2 337 ms 390 ms 405 ms 0%
Checkout 8.2 258 ms 304 ms 316 ms 0%
32 virtual users
Add to cart 8.23 1.34 s 1.58 s 1.62 s 0%
Cart 8.23 1.4 s 1.54 s 1.57 s 0%
Checkout 8.23 1.13 s 1.29 s 1.35 s 0%

k6 with a fixed number of virtual users, 61 to 66 s per level. The error rate counts responses that weren't a 200.

Discourse

Signed in

Step Requests/s Median p95 p99 Error rate
1 virtual user
Topic page 4.42 99.9 ms 129 ms 232 ms 0%
Topic JSON 2.23 50 ms 61.4 ms 72.5 ms 0%
Home page 2.21 87.6 ms 138 ms 260 ms 0%
Categories page 1.11 102 ms 122 ms 173 ms 0%
User activity page 1.1 62.7 ms 95.4 ms 211 ms 0%
4 virtual users
Topic page 7.87 224 ms 285 ms 630 ms 0%
Topic JSON 3.93 117 ms 146 ms 330 ms 0%
Home page 3.92 204 ms 256 ms 530 ms 0%
Categories page 1.97 237 ms 307 ms 573 ms 0%
User activity page 1.97 148 ms 184 ms 458 ms 0%
16 virtual users
Topic page 7.64 832 ms 1.04 s 1.28 s 0%
Topic JSON 3.87 722 ms 912 ms 1.1 s 0%
Home page 3.83 808 ms 1.07 s 1.31 s 0%
Categories page 1.94 829 ms 1.04 s 1.15 s 0%
User activity page 1.93 755 ms 864 ms 937 ms 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 165 26.4 ms 68.5 ms 90.5 ms 0%
Topic JSON 82.4 24.9 ms 67.5 ms 86.9 ms 0%
Home page 82.4 26.2 ms 68.3 ms 97.7 ms 0%
Categories page 41.2 26.1 ms 69.6 ms 87.4 ms 0%
User activity page 41.2 89 ms 140 ms 235 ms 0%

k6 with a fixed number of virtual users, 60 to 61 s per level, after a 21 s warmup. The error rate counts responses that weren't a 200. Discourse ran with 4 app workers and 1024 MB of Postgres shared buffers, what its installer picks for a 4 GB box. It added a 2 GB swapfile first, the way its installer does, and didn't need it. The container peaked at 2,537 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 18.8 15.3 ms 16.9 ms 19.9 ms 0%
Post page 47 7.61 ms 9.11 ms 12.7 ms 0%
Tag page 9.41 10.5 ms 12.1 ms 16.7 ms 0%
Author page 9.41 10.4 ms 12 ms 15.9 ms 0%
RSS feed 9.41 14.2 ms 16.2 ms 21.1 ms 0%
4 virtual users
Home page 21.9 47.1 ms 59.3 ms 76.1 ms 0%
Post page 54.7 33.8 ms 47.1 ms 58.2 ms 0%
Tag page 10.9 31.2 ms 43.2 ms 56.4 ms 0%
Author page 11 30.9 ms 42.6 ms 47.5 ms 0%
RSS feed 10.9 34.2 ms 46.8 ms 55.4 ms 0%
16 virtual users
Home page 21.2 190 ms 236 ms 253 ms 0%
Post page 53.2 158 ms 199 ms 219 ms 0%
Tag page 10.6 104 ms 143 ms 161 ms 0%
Author page 10.6 104 ms 134 ms 161 ms 0%
RSS feed 10.6 107 ms 143 ms 164 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 7.63 15.6 ms 18.7 ms 23.2 ms 0%
Post editor 22.9 5.5 ms 7.36 ms 10.6 ms 0%
Saving a draft 22.9 25.1 ms 32.4 ms 37.3 ms 0%
Member list 7.64 17.8 ms 20.9 ms 23.9 ms 0%
4 virtual users
Post list 9.87 18.7 ms 22.5 ms 33.6 ms 0%
Post editor 29.6 7.48 ms 10.6 ms 13.7 ms 0%
Saving a draft 29.7 110 ms 134 ms 159 ms 0%
Member list 9.88 21 ms 23.9 ms 29.3 ms 0%

k6 with a fixed number of virtual users, 60 s per level, after a 20 s warmup. The error rate counts responses that weren't a 200. Ghost ran the way its ghost-docker setup runs it: one Node process, and MySQL with its stock 128 MB buffer pool. Memory peaked with Ghost at 342 MB and MySQL at 623 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 3.48 37.4 ms 41.3 ms 43.6 ms 0%
Blog index 3.46 128 ms 140 ms 144 ms 0%
Blog post 10.4 11.7 ms 18.1 ms 20.3 ms 0%
Bread page 10.4 13 ms 14.7 ms 15.7 ms 0%
Location page 3.48 12.4 ms 14.3 ms 15.3 ms 0%
Site search 3.46 24.7 ms 39.4 ms 41.5 ms 0%
4 virtual users
Home page 5.78 96.5 ms 133 ms 159 ms 0%
Blog index 5.8 330 ms 430 ms 454 ms 0%
Blog post 17.3 29 ms 46.4 ms 60.4 ms 0%
Bread page 17.4 32.2 ms 45 ms 51.8 ms 0%
Location page 5.83 29.9 ms 41.9 ms 47.9 ms 0%
Site search 5.77 48.4 ms 90.7 ms 125 ms 0%
16 virtual users
Home page 6.2 295 ms 437 ms 555 ms 0%
Blog index 6.28 721 ms 871 ms 935 ms 0%
Blog post 18.7 169 ms 288 ms 390 ms 0%
Bread page 18.7 173 ms 271 ms 376 ms 0%
Location page 6.27 165 ms 296 ms 364 ms 0%
Site search 6.2 206 ms 321 ms 441 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 1.41 39.9 ms 44.3 ms 49.6 ms 0%
Page explorer 2.85 166 ms 176 ms 284 ms 0%
Page editor 4.24 82.8 ms 92.2 ms 197 ms 0%
Image library 1.41 30.2 ms 32.8 ms 116 ms 0%
Admin page search 1.41 16.6 ms 36.3 ms 40.5 ms 0%
4 virtual users
Admin dashboard 2.34 117 ms 252 ms 344 ms 0%
Page explorer 4.7 417 ms 643 ms 685 ms 0%
Page editor 7.06 189 ms 369 ms 436 ms 0%
Image library 2.35 98.2 ms 239 ms 308 ms 0%
Admin page search 2.34 43.2 ms 123 ms 188 ms 0%

k6 with a fixed number of virtual users, 60 s per level, after a 20 s warmup. The error rate counts responses that weren't a 200. Wagtail ran the way bakerydemo ships it: uWSGI with 2 workers of 4 threads each, whatever the box, and Postgres and Redis on stock settings. Memory peaked with Wagtail at 313 MB, Postgres at 182 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0.2% of busy CPU time stolen
RAM 4 GB 3.8 GiB
Storage 80 GB NVMe 77.4 GiB
Architecture x86_64 x86_64
Virtualization KVM KVM

Guests usually report slightly less RAM and disk than advertised because of kernel reservations and filesystem overhead.

Detected hardware

CPU model
AMD EPYC Processor
CPU cores
2
CPU frequency
4400 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
3.8 GiB
Swap reported
0 MiB
Disk reported
77.4 GiB
Virtualization reported
KVM
CPU steal
0.2% of busy CPU time stolen
Distro
Ubuntu 24.04.5 LTS
Kernel
6.8.0-142-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
rz.starter
Product line
High Frequency
Location
Miami
vCPU
2 shared vCPU
Architecture
x86_64
RAM
4 GB
Storage
80 GB NVMe
Virtualization
KVM
Network
Unknown
Transfer
4 TB
Port 25
On request
Monthly price at test time
$16.22
Hourly price at test time
$0.022
YABS version
v2026-09-20
Ran at
Oct 15, 2026, 07:31:10 UTC
Parser version
5

Run timeline

Queued
Oct 15, 2026, 07:30:00 UTC
First update from the server
Oct 15, 2026, 07:30:58 UTC
Completed
Oct 15, 2026, 09:04:49 UTC
Server deleted
Oct 15, 2026, 09:04:49 UTC
Cost of this run
$0.035
Watch party 0 watching

This party closed at . It's read only now.

Watch party

Loading the party