Skip to main content

Hetzner CPX41

Ashburn, VA

Benchmark complete
Finished Oct 12, 2026
Geekbench 7 single-core
1,202
Geekbench 7 multi-core
7,164
Disk 4K IOPS
48,568
fio random read and write, 50/50
Monthly price at test time
$141.49
51 multi-core points per dollar
Same price today

Server

  • Provider
    Hetzner
  • Plan
    CPX41
  • Location
    Ashburn, VA
  • vCPU
    8
  • RAM
    16 GB
  • Storage
    240 GB NVMe
  • Network
    Unknown
  • OS image
    ubuntu-24.04
  • Trigger
    Scheduled
  • Queued at
    Oct 12, 2026, 18:54:00 UTC
Visit Hetzner

CPU

Version Single-core Multi-core
Geekbench 7 1,202 7,164 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
1,308
64th of 129
6,158
6th of 103
Navigation
1,255
75th of 129
Single-core only
HTML5 Browser
1,092
75th of 129
Single-core only
PDF Viewer
1,348
58th of 129
Single-core only
Photo Library
1,173
60th of 129
8,080
10th of 103
Clang
962
93rd of 129
7,206
13th of 103
Text Processing
1,035
79th of 129
6,899
12th of 103
Asset Compression
1,219
71st of 129
9,486
11th of 103
HDR
1,225
60th of 129
4,512
16th of 103
Photo Editor
1,436
56th of 129
7,206
6th of 103
Ray Tracer
1,077
80th of 129
9,091
10th of 103
Structure from Motion
1,404
60th of 129
Single-core only
Game Physics
1,105
76th of 129
Single-core only
Video Encoder
1,146
73rd of 129
Single-core only
Audio Encoder
1,264
70th of 129
Single-core only
Video Player
1,292
69th of 129
Single-core only

Rank among the 129 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 59 GB/s 3 15.1%
Scale higher is better 55.5 GB/s 3 16.4%
Add higher is better 60 GB/s 3 18.5%
Triad higher is better 57.7 GB/s 3 16.6%

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 1,551/s 3 1.22%
RSA 4096 verifies higher is better 101,830/s 3 2.63%
SHA-256 higher is better 5.36 GB/s 3 3.89%
AES-256-GCM higher is better 23.1 GB/s 3 3.07%
ChaCha20-Poly1305 higher is better 15.3 GB/s 3 4.12%

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 6.02 ms 3 6.74%
Requests per second, 90th percentile higher is better 1,245/s 3 5.72%
Request latency, 99.9th percentile lower is better 13 ms 3 6.54%
Requests per second, average higher is better 1,182/s 3 5.47%

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

Disk

Block size Read Write Total
4K 94.7 MB/s (24,252 IOPS) 95 MB/s (24,316 IOPS) 189.7 MB/s (48,568 IOPS)
64K 1015.7 MB/s (16,251 IOPS) 1021.1 MB/s (16,337 IOPS) 1.99 GB/s (32,588 IOPS)
512K 1.55 GB/s (3,176 IOPS) 1.63 GB/s (3,345 IOPS) 3.18 GB/s (6,521 IOPS)
1M 1.59 GB/s (1,632 IOPS) 1.7 GB/s (1,741 IOPS) 3.29 GB/s (3,373 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 2.36 Gbps 2.93 Gbps
Eranium, Amsterdam, NL (100G) IPv4 2.22 Gbps 2.8 Gbps
Leaseweb, Singapore, SG (10G) IPv4 767 Mbps 983 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 3.06 Gbps 3.35 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 9.32 Gbps 9.15 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 3,119 0.321 ms
fdatasync 3,021 0.331 ms
fsync 1,354 0.738 ms
fsync_writethrough Not supported here n/a
open_sync 1,873 0.534 ms
Two 8 kB writes
open_datasync 1,669 0.599 ms
fdatasync 3,213 0.311 ms
fsync 1,712 0.584 ms
fsync_writethrough Not supported here n/a
open_sync 908 1.1 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,822 0.549 ms
2 * 8kB open_sync writes 906 1.1 ms
4 * 4kB open_sync writes 458 2.18 ms
8 * 2kB open_sync writes 228 4.38 ms
16 * 1kB open_sync writes 125 8.01 ms
fsync on a non-write descriptor
write, fsync, close 1,804 0.554 ms
write, close, fsync 1,640 0.61 ms
Non-synced 8 kB writes
write 1,125,009 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 1,157 0.834 ms 1.07 ms 1.53 ms 4.55 ms 0
Read/write (TPC-B like) 8 5,697 1.22 ms 2.4 ms 3.61 ms 7.5 ms 0
Read/write (TPC-B like) 32 8,964 2.45 ms 9.83 ms 17.6 ms 30.4 ms 0
Read only 1 14,255 0.065 ms 0.103 ms 0.132 ms 0.233 ms 0
Read only 8 186,339 0.037 ms 0.07 ms 0.085 ms 0.109 ms 0
Read only 32 195,063 0.149 ms 0.282 ms 0.35 ms 0.45 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.18 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 1,097 0.867 ms 1.1 ms 2.42 ms 5.48 ms 0
Read/write (TPC-B like) 8 5,695 1.2 ms 1.86 ms 7.63 ms 12.5 ms 0
Read/write (TPC-B like) 32 12,235 2.12 ms 5.41 ms 11.9 ms 24.3 ms 0
Read only 1 11,679 0.08 ms 0.125 ms 0.156 ms 0.347 ms 0
Read only 8 140,004 0.051 ms 0.087 ms 0.105 ms 0.148 ms 0
Read only 32 124,269 0.236 ms 0.421 ms 0.536 ms 1.07 ms 0

Scale 100 (10,000,000 accounts), loaded in 11 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 1 212 4,232 4.33 ms 6.91 ms 12.5 ms 0
Read/write 8 1,434 28,678 5.09 ms 9.56 ms 16.7 ms 0
Read/write 32 2,571 51,416 11.7 ms 20.7 ms 26.7 ms 0
Read only 1 617 9,872 1.55 ms 2.15 ms 2.62 ms 0
Read only 8 6,982 111,716 1.08 ms 1.55 ms 1.7 ms 0
Read only 32 6,476 103,613 4.74 ms 7.04 ms 8.43 ms 0

10 tables of 100,000 rows, loaded in 4.2 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 76,209 69,281 0.775 ms 1.57 ms 2.34 ms
1:1 set:get 73,086 36,543 0.807 ms 1.71 ms 2.61 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 1,823 7,912 11,497 253 ms
Express express-postgresjs 25,872 35,988 105,948 22.2 ms
Fastify fastify-postgres 25,218 35,734 119,047 21.8 ms
NestJS nestjs 15,101 17,885 61,813 36 ms
Nuxt nuxt 25,005 34,836 85,140 33.1 ms
FastAPI fastapi 12,725 16,134 48,043 81 ms
Django django-postgresql 5,705 6,626 17,164 108 ms
Rails rails 9,756 13,080 48,023 45.6 ms
Laravel laravel 2,637 2,938 5,180 111 ms
Symfony symfony 3,151 3,553 10,316 108 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.

WooCommerce

Page mix

Step Requests/s Median p95 p99 Error rate
8 virtual users
Home page 7.27 213 ms 257 ms 272 ms 0%
Shop page 7.27 289 ms 342 ms 370 ms 0%
Category page 7.27 181 ms 290 ms 334 ms 0%
Product page 7.27 196 ms 244 ms 271 ms 0%
Product search 7.27 172 ms 212 ms 231 ms 0%
32 virtual users
Home page 7.18 883 ms 1.07 s 1.15 s 0%
Shop page 7.18 1.24 s 1.48 s 1.59 s 0%
Category page 7.18 749 ms 1.26 s 1.41 s 0%
Product page 7.18 785 ms 959 ms 1.03 s 0%
Product search 7.18 688 ms 875 ms 971 ms 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 14.7 214 ms 252 ms 275 ms 0%
Cart 14.7 175 ms 209 ms 229 ms 0%
Checkout 14.7 135 ms 163 ms 181 ms 0%
32 virtual users
Add to cart 12.5 1.08 s 1.39 s 1.5 s 0%
Cart 12.5 866 ms 1.11 s 1.19 s 0%
Checkout 12.5 681 ms 882 ms 936 ms 0%

k6 with a fixed number of virtual users, 61 to 63 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 1.75 254 ms 317 ms 601 ms 0%
Topic JSON 0.893 130 ms 169 ms 185 ms 0%
Home page 0.893 220 ms 261 ms 438 ms 0%
Categories page 0.446 263 ms 298 ms 409 ms 0%
User activity page 0.43 160 ms 212 ms 383 ms 0%
4 virtual users
Topic page 6.78 265 ms 314 ms 552 ms 0%
Topic JSON 3.39 135 ms 161 ms 173 ms 0%
Home page 3.36 237 ms 276 ms 414 ms 0%
Categories page 1.72 281 ms 421 ms 656 ms 0%
User activity page 1.69 163 ms 193 ms 444 ms 0%
16 virtual users
Topic page 12.7 528 ms 679 ms 943 ms 0%
Topic JSON 6.36 389 ms 496 ms 700 ms 0%
Home page 6.34 495 ms 613 ms 837 ms 0%
Categories page 3.18 539 ms 691 ms 963 ms 0%
User activity page 3.16 419 ms 523 ms 716 ms 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 255 15.8 ms 30.3 ms 46 ms 0%
Topic JSON 127 14.7 ms 28.2 ms 43.7 ms 0%
Home page 127 16 ms 30.1 ms 46.1 ms 0%
Categories page 63.7 15.6 ms 30.3 ms 46.6 ms 0%
User activity page 63.7 89.6 ms 120 ms 199 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 4096 MB of Postgres shared buffers, what its installer picks for a 16 GB box. Its installer adds no swap on a box this big. The container peaked at 2,742 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 7.65 40.3 ms 51.2 ms 54.2 ms 0%
Post page 19.1 19.8 ms 25.1 ms 29.4 ms 0%
Tag page 3.81 24.5 ms 32.3 ms 35.3 ms 0%
Author page 3.81 25.4 ms 33.3 ms 36.3 ms 0%
RSS feed 3.81 25.5 ms 32 ms 36.3 ms 0%
4 virtual users
Home page 10.2 112 ms 141 ms 156 ms 0%
Post page 25.4 67.3 ms 98.1 ms 111 ms 0%
Tag page 5.1 63.6 ms 90.9 ms 101 ms 0%
Author page 5.09 72.9 ms 97.8 ms 107 ms 0%
RSS feed 5.09 74 ms 102 ms 109 ms 0%
16 virtual users
Home page 10.3 396 ms 455 ms 483 ms 0%
Post page 25.7 330 ms 391 ms 417 ms 0%
Tag page 5.14 218 ms 266 ms 297 ms 0%
Author page 5.13 213 ms 269 ms 295 ms 0%
RSS feed 5.13 224 ms 279 ms 294 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 4.48 32.2 ms 42.5 ms 45 ms 0%
Post editor 13.5 13 ms 16.5 ms 19.4 ms 0%
Saving a draft 13.5 33.3 ms 40.2 ms 46.2 ms 0%
Member list 4.5 40.6 ms 54.2 ms 60.5 ms 0%
4 virtual users
Post list 5.43 47.3 ms 62.5 ms 70 ms 0%
Post editor 16.3 23.3 ms 31.1 ms 35.8 ms 0%
Saving a draft 16.3 185 ms 243 ms 272 ms 0%
Member list 5.44 57.1 ms 75.2 ms 81.6 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 525 MB and MySQL at 625 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.31 103 ms 120 ms 130 ms 0%
Blog index 1.3 340 ms 382 ms 401 ms 0%
Blog post 3.89 33.5 ms 53.2 ms 60.8 ms 0%
Bread page 3.89 36.7 ms 44.6 ms 47.9 ms 0%
Location page 1.3 35 ms 42.9 ms 46 ms 0%
Site search 1.3 58.3 ms 104 ms 137 ms 0%
4 virtual users
Home page 2.3 268 ms 382 ms 415 ms 0%
Blog index 2.33 945 ms 1.29 s 1.34 s 0%
Blog post 6.91 67.7 ms 127 ms 171 ms 0%
Bread page 6.93 76.4 ms 125 ms 154 ms 0%
Location page 2.35 72.2 ms 118 ms 204 ms 0%
Site search 2.28 101 ms 254 ms 300 ms 0%
16 virtual users
Home page 2.8 653 ms 877 ms 1.1 s 0%
Blog index 2.9 1.74 s 2.08 s 2.24 s 0%
Blog post 8.45 369 ms 605 ms 777 ms 0%
Bread page 8.52 359 ms 627 ms 768 ms 0%
Location page 2.87 356 ms 502 ms 616 ms 0%
Site search 2.8 422 ms 626 ms 725 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.56 105 ms 130 ms 138 ms 0%
Page explorer 1.15 420 ms 521 ms 574 ms 0%
Page editor 1.7 193 ms 272 ms 365 ms 0%
Image library 0.56 77.2 ms 91.4 ms 669 ms 0%
Admin page search 0.56 43.5 ms 98 ms 102 ms 0%
4 virtual users
Admin dashboard 0.874 336 ms 642 ms 695 ms 0%
Page explorer 1.73 991 ms 2.35 s 2.98 s 0%
Page editor 2.62 541 ms 966 ms 1.05 s 0%
Image library 0.874 225 ms 434 ms 555 ms 0%
Admin page search 0.874 130 ms 356 ms 420 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 295 MB, Postgres at 148 MB, and Redis at 8 MB.

Advertised vs. measured

Advertised Measured
vCPU 8 8
CPU Shared vCPU 0% of busy CPU time stolen
RAM 16 GB 15.2 GiB
Storage 240 GB NVMe 225.2 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
8
CPU frequency
2445 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
15.2 GiB
Swap reported
0 MiB
Disk reported
225.2 GiB
Virtualization reported
KVM
CPU steal
0% of busy CPU time stolen
Distro
Ubuntu 24.04.4 LTS
Kernel
6.8.0-138-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
CPX41
Product line
regular_purpose
Location
Ashburn, VA
vCPU
8 shared vCPU
Architecture
x86_64
RAM
16 GB
Storage
240 GB NVMe
Virtualization
KVM
Network
Unknown
Transfer
4.4 TB
Port 25
On request
Monthly price at test time
$141.49
Hourly price at test time
$0.23
YABS version
v2026-09-20
Ran at
Oct 12, 2026, 18:54:46 UTC
Parser version
5

Run timeline

Queued
Oct 12, 2026, 18:54:00 UTC
First update from the server
Oct 12, 2026, 18:54:40 UTC
Completed
Oct 12, 2026, 20:26:17 UTC
Server deleted
Oct 12, 2026, 20:26:17 UTC
Cost of this run
$0.35
Watch party 0 watching

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

Watch party

Loading the party