Skip to main content

Cherry Servers Cloud VPS 4

Chicago, US

Benchmark complete
Finished Oct 10, 2026
Geekbench 7 single-core
587
Faster than 0% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
9,860
fio random read and write, 50/50
Monthly price at test time
$33.93
Same price today

Server

  • Provider
    Cherry Servers
  • Plan
    Cloud VPS 4
  • Location
    Chicago, US
  • vCPU
    2
  • RAM
    4 GB
  • Storage
    80 GB SSD
  • Network
    1 Gbps
  • OS image
    ubuntu_24_04_64bit
  • Trigger
    Scheduled
  • Queued at
    Oct 10, 2026, 08:45:00 UTC
Visit Cherry Servers

Referral link. If you sign up through it, I may get paid.

Skip the referral How this works

CPU

Version Single-core Multi-core
Geekbench 7 587 Skipped Geekbench Browser

Multi-core was skipped because Geekbench 7 needs about 4.2 GB of free memory to run 4 threads, and this server didn't have that much. Single-core needs much less, so it still ran.

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
635
70th of 70
Single-core only
Navigation
608
70th of 70
Single-core only
HTML5 Browser
537
70th of 70
Single-core only
PDF Viewer
576
70th of 70
Single-core only
Photo Library
525
68th of 70
Single-core only
Clang
490
70th of 70
Single-core only
Text Processing
535
69th of 70
Single-core only
Asset Compression
592
69th of 70
Single-core only
HDR
617
67th of 70
Single-core only
Photo Editor
585
67th of 70
Single-core only
Ray Tracer
614
69th of 70
Single-core only
Structure from Motion
647
70th of 70
Single-core only
Game Physics
560
69th of 70
Single-core only
Video Encoder
586
68th of 70
Single-core only
Audio Encoder
644
68th of 70
Single-core only
Video Player
670
65th of 70
Single-core only

Rank among the 70 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 66.1 GB/s 3 9.57%
Scale higher is better 42.9 GB/s 3 7.41%
Add higher is better 46.5 GB/s 3 8.77%
Triad higher is better 46.4 GB/s 3 9.86%

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 378/s 3 4.65%
RSA 4096 verifies higher is better 24,219/s 3 1.39%
SHA-256 higher is better 1.35 GB/s 3 0.776%
AES-256-GCM higher is better 6.27 GB/s 3 0.895%
ChaCha20-Poly1305 higher is better 3.71 GB/s 3 0.487%

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 5.44 ms 3 0.612%
Requests per second, 90th percentile higher is better 373/s 3 0.82%
Request latency, 99.9th percentile lower is better 494 ms 3 0.415%
Requests per second, average higher is better 367/s 3 0.571%

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

Disk

Block size Read Write Total
4K 19.3 MB/s (4,930 IOPS) 19.3 MB/s (4,930 IOPS) 38.5 MB/s (9,860 IOPS)
64K 198.5 MB/s (3,176 IOPS) 199.6 MB/s (3,193 IOPS) 398.1 MB/s (6,369 IOPS)
512K 189.9 MB/s (379 IOPS) 200 MB/s (400 IOPS) 389.9 MB/s (779 IOPS)
1M 184.6 MB/s (184 IOPS) 196.9 MB/s (196 IOPS) 381.6 MB/s (380 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 10.6 Mbps 9.2 Mbps
Eranium, Amsterdam, NL (100G) IPv4 10.2 Mbps 9.2 Mbps
Leaseweb, Singapore, SG (10G) IPv4 10 Mbps 9.1 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 10.6 Mbps 9.2 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 10 Mbps 9.2 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 2,868 0.349 ms
fdatasync 2,796 0.358 ms
fsync 1,855 0.539 ms
fsync_writethrough Not supported here n/a
open_sync 2,014 0.497 ms
Two 8 kB writes
open_datasync 1,538 0.65 ms
fdatasync 2,635 0.38 ms
fsync 1,720 0.581 ms
fsync_writethrough Not supported here n/a
open_sync 956 1.05 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,983 0.504 ms
2 * 8kB open_sync writes 1,019 0.981 ms
4 * 4kB open_sync writes 543 1.84 ms
8 * 2kB open_sync writes 253 3.95 ms
16 * 1kB open_sync writes 110 9.11 ms
fsync on a non-write descriptor
write, fsync, close 1,520 0.658 ms
write, close, fsync 1,767 0.566 ms
Non-synced 8 kB writes
write 284,923 0.004 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) 1 820 0.615 ms 0.764 ms 0.924 ms 485 ms 0
Read/write (TPC-B like) 8 2,653 1.43 ms 2.63 ms 3.83 ms 487 ms 0
Read/write (TPC-B like) 32 2,925 4.27 ms 14.3 ms 227 ms 507 ms 0
Read only 1 9,798 0.048 ms 0.076 ms 0.096 ms 0.182 ms 0
Read only 8 34,004 0.105 ms 0.215 ms 0.281 ms 0.714 ms 0
Read only 32 37,068 0.347 ms 0.722 ms 1.25 ms 10.6 ms 0

Scale 10 (1,000,000 accounts), loaded in 2.42 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) 1 712 0.718 ms 0.947 ms 3.9 ms 6.63 ms 0
Read/write (TPC-B like) 8 2,306 1.64 ms 3.67 ms 15.6 ms 479 ms 0
Read/write (TPC-B like) 32 3,127 4.73 ms 17.6 ms 49.4 ms 500 ms 0
Read only 1 6,956 0.065 ms 0.134 ms 0.226 ms 1.38 ms 0
Read only 8 26,900 0.133 ms 0.274 ms 0.369 ms 1.7 ms 0
Read only 32 28,516 0.474 ms 0.94 ms 1.75 ms 487 ms 0

Scale 100 (10,000,000 accounts), loaded in 28.7 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 1 198 3,959 2.86 ms 4.33 ms 14.2 ms 0
Read/write 8 539 10,785 7.17 ms 18.6 ms 419 ms 0
Read/write 32 623 12,452 24.8 ms 419 ms 530 ms 0
Read only 1 362 5,791 1.37 ms 1.82 ms 2.11 ms 0
Read only 8 1,248 19,960 3.13 ms 5.57 ms 8.28 ms 0
Read only 32 1,214 19,416 12.5 ms 25.3 ms 511 ms 0

10 tables of 100,000 rows, loaded in 8.8 s. 60 to 61 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 31,260 28,418 0.983 ms 2 ms 496 ms
1:1 set:get 29,113 14,556 1.06 ms 2.26 ms 496 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 517 1,809 2,641 872 ms
Express express-postgresjs 8,425 10,807 24,215 513 ms
Fastify fastify-postgres 8,480 11,732 26,261 510 ms
NestJS nestjs 3,881 4,339 14,370 541 ms
Nuxt nuxt 6,817 10,216 25,735 511 ms
FastAPI fastapi 2,818 3,635 13,549 605 ms
Django django-postgresql 1,120 1,251 2,654 710 ms
Rails rails 2,018 2,548 8,770 534 ms
Laravel laravel 656 687 1,318 709 ms
Symfony symfony 807 904 2,391 682 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 2 890 ms 1.06 s 1.57 s 0%
Shop page 2 1.04 s 1.69 s 1.75 s 0%
Category page 2 809 ms 1.08 s 1.18 s 0%
Product page 2 841 ms 1.01 s 1.05 s 0%
Product search 2 741 ms 941 ms 968 ms 0%
32 virtual users
Home page 1.94 3 s 4.07 s 4.19 s 0%
Shop page 1.94 4.06 s 4.99 s 5.56 s 0%
Category page 1.94 3.05 s 4.11 s 5.01 s 0%
Product page 1.94 3.04 s 3.84 s 4.22 s 0%
Product search 1.94 2.82 s 3.59 s 3.88 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 3.74 912 ms 1.1 s 1.61 s 0%
Cart 3.74 836 ms 988 ms 1.03 s 0%
Checkout 3.74 700 ms 886 ms 928 ms 0%
32 virtual users
Add to cart 3.48 3.24 s 4.19 s 4.76 s 0%
Cart 3.48 3.06 s 4.02 s 4.24 s 0%
Checkout 3.48 2.63 s 3.13 s 3.63 s 0%

k6 with a fixed number of virtual users, 61 to 67 s per level. The error rate counts responses that weren't a 200.

Advertised vs. measured

Advertised Measured
vCPU 2 4
CPU Shared vCPU 43.5% of busy CPU time stolen
RAM 4 GB 3.8 GiB
Storage 80 GB SSD 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-Milan Processor
CPU cores
4
CPU frequency
2850 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
43.5% 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
No

Advertised at test time

Plan
Cloud VPS 4
Product line
Cloud VPS
Location
Chicago, US
vCPU
2 shared vCPU
Architecture
x86_64
RAM
4 GB
Storage
80 GB SSD
Virtualization
KVM
Network
1 Gbps
Transfer
5 TB
Port 25
Unknown
Monthly price at test time
$33.93
Hourly price at test time
$0.059
YABS version
v2026-09-20
Ran at
Oct 10, 2026, 11:47:43 UTC
Parser version
5

Run timeline

Queued
Oct 10, 2026, 08:45:00 UTC
First update from the server
Oct 10, 2026, 08:47:38 UTC
Completed
Oct 10, 2026, 10:16:41 UTC
Server deleted
Oct 10, 2026, 10:16:41 UTC
Cost of this run
$0.089
Geekbench 7, multi-core Skipped, not enough free memory 0 of 0 Skipped
Watch party 0 watching

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

Watch party

Loading the party