Skip to main content

Hetzner CPX31

Hillsboro, OR

Benchmark complete
Finished Oct 14, 2026
Geekbench 7 single-core
1,375
Faster than 81% of 4 vCPU plans
Geekbench 7 multi-core
4,930
Faster than 86% of 4 vCPU plans
Disk 4K IOPS
56,731
fio random read and write, 50/50
Monthly price at test time
$73.49
67 multi-core points per dollar
Same price today

Server

  • Provider
    Hetzner
  • Plan
    CPX31
  • Location
    Hillsboro, OR
  • vCPU
    4
  • RAM
    8 GB
  • Storage
    160 GB NVMe
  • Network
    Unknown
  • OS image
    ubuntu-24.04
  • Trigger
    Scheduled
  • Queued at
    Oct 14, 2026, 14:23:00 UTC
Visit Hetzner

Latest runs of this plan

Full history of this plan

CPU

Version Single-core Multi-core
Geekbench 7 1,375 4,930 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
1,433
54th of 164
4,432
19th of 121
Navigation
1,445
50th of 164
Single-core only
HTML5 Browser
1,330
54th of 164
Single-core only
PDF Viewer
1,413
62nd of 164
Single-core only
Photo Library
1,294
54th of 164
4,911
22nd of 121
Clang
1,164
64th of 164
4,660
26th of 121
Text Processing
1,258
56th of 164
4,535
25th of 121
Asset Compression
1,407
57th of 164
5,467
24th of 121
HDR
1,380
51st of 164
4,414
18th of 121
Photo Editor
1,537
54th of 164
6,079
12th of 121
Ray Tracer
1,320
59th of 164
5,168
27th of 121
Structure from Motion
1,698
34th of 164
Single-core only
Game Physics
1,299
60th of 164
Single-core only
Video Encoder
1,237
64th of 164
Single-core only
Audio Encoder
1,420
55th of 164
Single-core only
Video Player
1,449
56th of 164
Single-core only

Rank among the 164 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 75.9 GB/s 3 18.6%
Scale higher is better 54.1 GB/s 3 15.1%
Add higher is better 57.6 GB/s 3 18.2%
Triad higher is better 57.3 GB/s 3 18.6%

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 845/s 3 0.476%
RSA 4096 verifies higher is better 55,952/s 3 0.599%
SHA-256 higher is better 3.16 GB/s 3 0.862%
AES-256-GCM higher is better 15 GB/s 3 0.379%
ChaCha20-Poly1305 higher is better 8.54 GB/s 3 0.389%

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 4.69 ms 3 0.197%
Requests per second, 90th percentile higher is better 814/s 3 0.75%
Request latency, 99.9th percentile lower is better 10.4 ms 3 2.22%
Requests per second, average higher is better 801/s 3 0.776%

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

Disk

Block size Read Write Total
4K 110.7 MB/s (28,328 IOPS) 111 MB/s (28,403 IOPS) 221.6 MB/s (56,731 IOPS)
64K 1.02 GB/s (16,717 IOPS) 1.03 GB/s (16,805 IOPS) 2.05 GB/s (33,522 IOPS)
512K 1.63 GB/s (3,333 IOPS) 1.71 GB/s (3,510 IOPS) 3.34 GB/s (6,843 IOPS)
1M 1.82 GB/s (1,868 IOPS) 1.95 GB/s (1,992 IOPS) 3.77 GB/s (3,860 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 1.16 Gbps 1.38 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.26 Gbps 1.5 Gbps
Leaseweb, Singapore, SG (10G) IPv4 961 Mbps 1.13 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 4.39 Gbps 7.61 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 2.27 Gbps 3.2 Gbps

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 3,978 0.251 ms
fdatasync 3,429 0.292 ms
fsync 2,084 0.48 ms
fsync_writethrough Not supported here n/a
open_sync 2,280 0.439 ms
Two 8 kB writes
open_datasync 1,871 0.534 ms
fdatasync 3,566 0.28 ms
fsync 2,002 0.499 ms
fsync_writethrough Not supported here n/a
open_sync 1,034 0.967 ms
open_sync at different write sizes
1 * 16kB open_sync write 2,115 0.473 ms
2 * 8kB open_sync writes 1,074 0.931 ms
4 * 4kB open_sync writes 570 1.75 ms
8 * 2kB open_sync writes 241 4.16 ms
16 * 1kB open_sync writes 116 8.63 ms
fsync on a non-write descriptor
write, fsync, close 2,135 0.468 ms
write, close, fsync 1,977 0.506 ms
Non-synced 8 kB writes
write 1,331,546 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 1,279 0.741 ms 1.03 ms 1.5 ms 2.6 ms 0
Read/write (TPC-B like) 8 6,274 1.1 ms 2.26 ms 3.38 ms 6.15 ms 0
Read/write (TPC-B like) 32 7,029 3.35 ms 11.8 ms 19.9 ms 34.1 ms 0
Read only 1 15,126 0.062 ms 0.095 ms 0.124 ms 0.198 ms 0
Read only 8 94,950 0.075 ms 0.153 ms 0.201 ms 0.298 ms 0
Read only 32 118,802 0.234 ms 0.424 ms 0.562 ms 0.843 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.01 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 1,157 0.799 ms 1.2 ms 1.9 ms 4.22 ms 0
Read/write (TPC-B like) 8 6,490 1.09 ms 1.75 ms 5.73 ms 9.91 ms 0
Read/write (TPC-B like) 32 8,542 3.33 ms 6.66 ms 11.3 ms 23 ms 0
Read only 1 12,392 0.076 ms 0.115 ms 0.145 ms 0.227 ms 0
Read only 8 72,776 0.099 ms 0.196 ms 0.256 ms 0.503 ms 0
Read only 32 89,749 0.319 ms 0.561 ms 0.729 ms 1.15 ms 0

Scale 100 (10,000,000 accounts), loaded in 10 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 1 249 4,978 3.75 ms 5.77 ms 9.56 ms 0
Read/write 8 1,117 22,338 6.67 ms 11.9 ms 16.4 ms 0
Read/write 32 1,689 33,778 18.6 ms 30.3 ms 37.6 ms 0
Read only 1 656 10,498 1.44 ms 2.03 ms 2.48 ms 0
Read only 8 3,552 56,840 2.07 ms 3.75 ms 4.57 ms 0
Read only 32 3,652 58,436 8.58 ms 11.9 ms 14.5 ms 0

10 tables of 100,000 rows, loaded in 4.6 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 95,295 86,632 0.639 ms 1.3 ms 1.91 ms
1:1 set:get 100,689 50,344 0.607 ms 1.28 ms 1.94 ms

1,000,000 keys of 32 bytes. 64 connections over 4 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 1,308 4,600 6,345 325 ms
Express express-postgresjs 15,441 22,129 65,935 35.8 ms
Fastify fastify-postgres 15,300 22,523 68,724 35.2 ms
NestJS nestjs 9,609 10,858 36,617 50.6 ms
Nuxt nuxt 13,913 20,893 65,847 45.8 ms
FastAPI fastapi 7,656 9,155 34,913 111 ms
Django django-postgresql 3,649 4,087 9,963 214 ms
Rails rails 6,006 7,886 32,592 62.1 ms
Laravel laravel 1,509 1,643 3,101 204 ms
Symfony symfony 2,031 2,179 6,176 141 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 4.67 343 ms 453 ms 499 ms 0%
Shop page 4.67 463 ms 605 ms 649 ms 0%
Category page 4.67 289 ms 513 ms 582 ms 0%
Product page 4.67 317 ms 418 ms 451 ms 0%
Product search 4.67 282 ms 376 ms 402 ms 0%
32 virtual users
Home page 4.44 1.36 s 1.57 s 1.64 s 0%
Shop page 4.44 1.76 s 1.99 s 2.1 s 0%
Category page 4.44 1.42 s 1.82 s 2.01 s 0%
Product page 4.44 1.34 s 1.55 s 1.62 s 0%
Product search 4.44 1.2 s 1.37 s 1.41 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 8.95 355 ms 468 ms 503 ms 0%
Cart 8.95 302 ms 394 ms 449 ms 0%
Checkout 8.95 241 ms 310 ms 347 ms 0%
32 virtual users
Add to cart 8.69 1.37 s 1.61 s 1.7 s 0%
Cart 8.69 1.25 s 1.45 s 1.51 s 0%
Checkout 8.69 1.04 s 1.22 s 1.3 s 0%

k6 with a fixed number of virtual users, 61 to 65 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 2.22 205 ms 241 ms 393 ms 0%
Topic JSON 1.11 105 ms 125 ms 214 ms 0%
Home page 1.11 181 ms 208 ms 220 ms 0%
Categories page 0.562 214 ms 256 ms 362 ms 0%
User activity page 0.546 125 ms 166 ms 212 ms 0%
4 virtual users
Topic page 8.15 212 ms 325 ms 528 ms 0%
Topic JSON 4.08 110 ms 156 ms 207 ms 0%
Home page 4.07 189 ms 260 ms 465 ms 0%
Categories page 2.07 217 ms 393 ms 537 ms 0%
User activity page 2.02 130 ms 218 ms 324 ms 0%
16 virtual users
Topic page 8.27 807 ms 1.02 s 1.22 s 0%
Topic JSON 4.12 607 ms 806 ms 1.05 s 0%
Home page 4.14 752 ms 943 ms 1.23 s 0%
Categories page 2.07 823 ms 988 ms 1.28 s 0%
User activity page 2.08 641 ms 873 ms 1.1 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 180 21.5 ms 43.3 ms 64.4 ms 0%
Topic JSON 89.9 20 ms 41.8 ms 65.8 ms 0%
Home page 89.8 21.6 ms 44.2 ms 67.6 ms 0%
Categories page 45 21 ms 43.5 ms 67.5 ms 0%
User activity page 45 134 ms 181 ms 299 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 8 app workers and 2048 MB of Postgres shared buffers, what its installer picks for a 8 GB box. Its installer adds no swap on a box this big. The container peaked at 2,785 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 9.93 28.4 ms 37.6 ms 50.6 ms 0%
Post page 24.8 15.1 ms 19.5 ms 24.3 ms 0%
Tag page 4.96 19.1 ms 26 ms 36.1 ms 0%
Author page 4.96 19.5 ms 27.5 ms 31.3 ms 0%
RSS feed 4.95 20.9 ms 30.2 ms 38.8 ms 0%
4 virtual users
Home page 12.5 83.1 ms 105 ms 120 ms 0%
Post page 31.3 59.6 ms 82.5 ms 96.3 ms 0%
Tag page 6.28 54.6 ms 74.9 ms 87.1 ms 0%
Author page 6.26 53.5 ms 74.6 ms 84.5 ms 0%
RSS feed 6.26 58.5 ms 81.7 ms 92.9 ms 0%
16 virtual users
Home page 12.4 338 ms 398 ms 436 ms 0%
Post page 31 266 ms 333 ms 364 ms 0%
Tag page 6.21 189 ms 237 ms 272 ms 0%
Author page 6.15 190 ms 237 ms 258 ms 0%
RSS feed 6.16 192 ms 238 ms 265 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 5.18 27.4 ms 38.8 ms 45.6 ms 0%
Post editor 15.6 10.7 ms 14.5 ms 19.5 ms 0%
Saving a draft 15.6 28.9 ms 36.9 ms 45.7 ms 0%
Member list 5.18 34.5 ms 49.8 ms 59.1 ms 0%
4 virtual users
Post list 6.99 36.2 ms 46.6 ms 54.7 ms 0%
Post editor 21 18 ms 24.7 ms 31.8 ms 0%
Saving a draft 21 141 ms 177 ms 190 ms 0%
Member list 7.01 41.8 ms 52.9 ms 61.7 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 536 MB and MySQL at 625 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.54 84.3 ms 102 ms 115 ms 0%
Blog index 1.54 279 ms 326 ms 346 ms 0%
Blog post 4.62 28.7 ms 46.5 ms 54.9 ms 0%
Bread page 4.62 31.8 ms 40.8 ms 55.8 ms 0%
Location page 1.54 30.5 ms 39.4 ms 53 ms 0%
Site search 1.53 44.2 ms 79.4 ms 91.6 ms 0%
4 virtual users
Home page 2.74 210 ms 358 ms 441 ms 0%
Blog index 2.76 718 ms 1.21 s 1.27 s 0%
Blog post 8.19 51 ms 103 ms 145 ms 0%
Bread page 8.21 58.1 ms 100 ms 116 ms 0%
Location page 2.76 59.2 ms 101 ms 123 ms 0%
Site search 2.73 82.3 ms 190 ms 258 ms 0%
16 virtual users
Home page 3.34 548 ms 671 ms 758 ms 0%
Blog index 3.4 1.48 s 1.7 s 1.84 s 0%
Blog post 10 308 ms 440 ms 528 ms 0%
Bread page 10 325 ms 460 ms 555 ms 0%
Location page 3.35 322 ms 449 ms 511 ms 0%
Site search 3.32 373 ms 540 ms 607 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.676 88.9 ms 117 ms 122 ms 0%
Page explorer 1.39 340 ms 411 ms 482 ms 0%
Page editor 2.05 161 ms 207 ms 304 ms 0%
Image library 0.676 66.1 ms 75.5 ms 508 ms 0%
Admin page search 0.676 42.5 ms 79.2 ms 87.2 ms 0%
4 virtual users
Admin dashboard 0.918 295 ms 665 ms 752 ms 0%
Page explorer 1.9 897 ms 2.19 s 2.76 s 0%
Page editor 2.85 449 ms 912 ms 1.06 s 0%
Image library 0.951 260 ms 581 ms 652 ms 0%
Admin page search 0.918 121 ms 430 ms 534 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. 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 296 MB, Postgres at 151 MB, and Redis at 25 MB.

Advertised vs. measured

Advertised Measured
vCPU 4 4
CPU Shared vCPU 0% of busy CPU time stolen
RAM 8 GB 7.6 GiB
Storage 160 GB NVMe 150.1 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-Rome Processor
CPU cores
4
CPU frequency
2445 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
7.6 GiB
Swap reported
0 MiB
Disk reported
150.1 GiB
Virtualization reported
KVM
CPU steal
0% of busy CPU time stolen
Distro
Ubuntu 24.04.4 LTS
Kernel
6.8.0-139-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
CPX31
Product line
regular_purpose
Location
Hillsboro, OR
vCPU
4 shared vCPU
Architecture
x86_64
RAM
8 GB
Storage
160 GB NVMe
Virtualization
KVM
Network
Unknown
Transfer
3.3 TB
Port 25
On request
Monthly price at test time
$73.49
Hourly price at test time
$0.12
YABS version
v2026-09-20
Ran at
Oct 14, 2026, 14:23:41 UTC
Parser version
5

Run timeline

Queued
Oct 14, 2026, 14:23:00 UTC
First update from the server
Oct 14, 2026, 14:23:29 UTC
Completed
Oct 14, 2026, 15:58:11 UTC
Server deleted
Oct 14, 2026, 15:58:11 UTC
Cost of this run
$0.19
Watch party 0 watching

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

Watch party

Loading the party