Skip to main content

UpCloud Premium 4 vCPU / 8 GB

Chicago #1

Benchmark complete
Finished Oct 16, 2026
Geekbench 7 single-core
1,798
Faster than 100% of 4 vCPU plans
Geekbench 7 multi-core
7,420
Faster than 100% of 4 vCPU plans
Disk 4K IOPS
20,220
fio random read and write, 50/50
Monthly price at test time
€54.00 EUR
117 multi-core points per dollar
Same price today

Server

  • Provider
    UpCloud
  • Plan
    Premium 4 vCPU / 8 GB
  • Location
    Chicago #1
  • vCPU
    4
  • RAM
    8 GB
  • Storage
    100 GB NVMe
  • Network
    Unknown
  • OS image
    01000000-0000-4000-8000-000030240200
  • Trigger
    Scheduled
  • Queued at
    Oct 16, 2026, 17:54:00 UTC
Visit UpCloud

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

Latest runs of this plan

Full history of this plan

CPU

Version Single-core Multi-core
Geekbench 7 1,798 7,420 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
1,737
35th of 216
6,068
8th of 147
Navigation
1,355
86th of 216
Single-core only
HTML5 Browser
2,412
4th of 216
Single-core only
PDF Viewer
1,990
22nd of 216
Single-core only
Photo Library
1,939
14th of 216
8,773
7th of 147
Clang
1,289
66th of 216
5,151
28th of 147
Text Processing
1,234
79th of 216
6,910
13th of 147
Asset Compression
2,323
5th of 216
8,342
17th of 147
HDR
1,824
29th of 216
6,785
6th of 147
Photo Editor
2,798
7th of 216
11,560
1st of 147
Ray Tracer
1,178
114th of 216
7,409
17th of 147
Structure from Motion
2,322
8th of 216
Single-core only
Game Physics
1,984
9th of 216
Single-core only
Video Encoder
1,555
41st of 216
Single-core only
Audio Encoder
1,802
26th of 216
Single-core only
Video Player
1,904
23rd of 216
Single-core only

Rank among the 216 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 116 GB/s 3 10.2%
Scale higher is better 95.6 GB/s 3 16.7%
Add higher is better 99 GB/s 3 16.8%
Triad higher is better 101 GB/s 3 16%

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 3,475/s 3 1.21%
RSA 4096 verifies higher is better 94,825/s 3 1.43%
SHA-256 higher is better 5.19 GB/s 3 2.96%
AES-256-GCM higher is better 83.1 GB/s 3 2.05%
ChaCha20-Poly1305 higher is better 23.3 GB/s 3 0.997%

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 4.24 ms 3 1.9%
Requests per second, 90th percentile higher is better 987/s 3 8.29%
Request latency, 99.9th percentile lower is better 11.8 ms 3 19%
Requests per second, average higher is better 890/s 3 2.5%

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

Disk

Block size Read Write Total
4K 39.5 MB/s (10,099 IOPS) 39.5 MB/s (10,121 IOPS) 79 MB/s (20,220 IOPS)
64K 367 MB/s (5,872 IOPS) 369 MB/s (5,903 IOPS) 736 MB/s (11,775 IOPS)
512K 374.4 MB/s (748 IOPS) 394.3 MB/s (788 IOPS) 768.6 MB/s (1,536 IOPS)
1M 377.6 MB/s (377 IOPS) 402.7 MB/s (402 IOPS) 780.3 MB/s (779 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 764 Mbps 990 Mbps
Eranium, Amsterdam, NL (100G) IPv4 975 Mbps 1.01 Gbps
Leaseweb, Singapore, SG (10G) IPv4 716 Mbps 870 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.03 Gbps 1.04 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.06 Gbps 1.06 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 3,639 0.275 ms
fdatasync 5,078 0.197 ms
fsync 4,128 0.242 ms
fsync_writethrough Not supported here n/a
open_sync 4,315 0.232 ms
Two 8 kB writes
open_datasync 1,519 0.658 ms
fdatasync 2,720 0.368 ms
fsync 1,512 0.661 ms
fsync_writethrough Not supported here n/a
open_sync 743 1.35 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,509 0.663 ms
2 * 8kB open_sync writes 787 1.27 ms
4 * 4kB open_sync writes 385 2.6 ms
8 * 2kB open_sync writes 173 5.79 ms
16 * 1kB open_sync writes 119 8.44 ms
fsync on a non-write descriptor
write, fsync, close 3,708 0.27 ms
write, close, fsync 4,322 0.231 ms
Non-synced 8 kB writes
write 2,857,424 0 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 1,544 0.344 ms 1.79 ms 3.81 ms 7.3 ms 0
Read/write (TPC-B like) 8 6,569 0.745 ms 3.6 ms 7.05 ms 20.2 ms 0
Read/write (TPC-B like) 32 13,368 1.41 ms 6.7 ms 14.7 ms 40.5 ms 0
Read only 1 77,224 0.012 ms 0.019 ms 0.024 ms 0.035 ms 0
Read only 8 299,030 0.023 ms 0.051 ms 0.067 ms 0.091 ms 0
Read only 32 273,364 0.102 ms 0.181 ms 0.228 ms 0.31 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.06 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 2,808 0.277 ms 0.421 ms 0.926 ms 7.92 ms 0
Read/write (TPC-B like) 8 10,138 0.444 ms 0.896 ms 4.89 ms 68.9 ms 0
Read/write (TPC-B like) 32 10,752 1.3 ms 3.89 ms 24.7 ms 99.8 ms 0
Read only 1 60,775 0.014 ms 0.022 ms 0.028 ms 0.044 ms 0
Read only 8 215,428 0.033 ms 0.068 ms 0.089 ms 0.129 ms 0
Read only 32 220,217 0.127 ms 0.24 ms 0.309 ms 0.44 ms 0

Scale 100 (10,000,000 accounts), loaded in 10.3 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 1 635 12,696 1.37 ms 2.11 ms 5.99 ms 0
Read/write 8 1,944 38,875 3.19 ms 6.79 ms 29.2 ms 0
Read/write 32 3,136 62,725 8.43 ms 18 ms 60 ms 0
Read only 1 2,132 34,113 0.395 ms 0.841 ms 1.89 ms 0
Read only 8 7,243 115,895 1.06 ms 1.93 ms 2.62 ms 0
Read only 32 5,897 94,358 5.28 ms 7.57 ms 9.56 ms 0

10 tables of 100,000 rows, loaded in 4.1 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 155,063 140,966 0.343 ms 1.52 ms 3.58 ms
1:1 set:get 147,339 73,669 0.351 ms 1.69 ms 3.74 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 1,928 8,417 11,880 261 ms
Express express-postgresjs 14,059 36,857 177,948 36.2 ms
Fastify fastify-postgres 20,363 26,294 135,198 34.6 ms
NestJS nestjs 27,063 26,109 100,931 28 ms
Nuxt nuxt 20,008 33,662 192,824 38.6 ms
FastAPI fastapi 18,962 22,782 94,073 56.6 ms
Django django-postgresql 7,747 8,178 26,852 124 ms
Rails rails 12,043 18,083 89,309 44.7 ms
Laravel laravel 2,934 3,317 6,761 202 ms
Symfony symfony 2,828 2,513 11,938 121 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 5.06 316 ms 491 ms 536 ms 0%
Shop page 5.06 410 ms 620 ms 729 ms 0%
Category page 5.06 264 ms 466 ms 561 ms 0%
Product page 5.06 288 ms 450 ms 516 ms 0%
Product search 5.06 258 ms 408 ms 447 ms 0%
32 virtual users
Home page 5.44 1 s 1.63 s 1.8 s 0%
Shop page 5.44 1.34 s 2.21 s 2.36 s 0%
Category page 5.44 1.05 s 1.89 s 2.13 s 0%
Product page 5.44 956 ms 1.6 s 1.68 s 0%
Product search 5.44 864 ms 1.42 s 1.48 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 15.7 199 ms 276 ms 316 ms 0%
Cart 15.7 173 ms 240 ms 266 ms 0%
Checkout 15.7 137 ms 189 ms 210 ms 0%
32 virtual users
Add to cart 14.1 842 ms 1.01 s 1.12 s 0%
Cart 14.1 760 ms 909 ms 1.03 s 0%
Checkout 14.1 654 ms 784 ms 825 ms 0%

k6 with a fixed number of virtual users, 61 to 64 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 3.56 116 ms 209 ms 392 ms 0%
Topic JSON 1.79 59.1 ms 87.3 ms 96.9 ms 0%
Home page 1.79 105 ms 169 ms 307 ms 0%
Categories page 0.893 118 ms 176 ms 433 ms 0%
User activity page 0.893 75.9 ms 120 ms 194 ms 0%
4 virtual users
Topic page 9.09 169 ms 370 ms 667 ms 0%
Topic JSON 4.55 90.8 ms 177 ms 266 ms 0%
Home page 4.55 160 ms 308 ms 466 ms 0%
Categories page 2.3 168 ms 391 ms 455 ms 0%
User activity page 2.26 104 ms 213 ms 358 ms 0%
16 virtual users
Topic page 6.72 1.01 s 1.44 s 2.04 s 0%
Topic JSON 3.4 769 ms 1.11 s 1.3 s 0%
Home page 3.35 975 ms 1.42 s 1.69 s 0%
Categories page 1.69 1.02 s 1.4 s 1.92 s 0%
User activity page 1.7 815 ms 1.11 s 1.26 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 151 24.9 ms 58.6 ms 86.6 ms 0%
Topic JSON 75.3 23.7 ms 57.3 ms 85.9 ms 0%
Home page 75.3 25.3 ms 59.2 ms 90.5 ms 0%
Categories page 37.7 24.8 ms 55.2 ms 90.5 ms 0%
User activity page 37.7 159 ms 256 ms 452 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 3,023 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 11.9 20.4 ms 37.3 ms 46.3 ms 0%
Post page 29.8 12.5 ms 25 ms 33.1 ms 0%
Tag page 5.96 13.4 ms 24.8 ms 29.1 ms 0%
Author page 5.96 13.5 ms 26 ms 31.1 ms 0%
RSS feed 5.96 15 ms 29.1 ms 36 ms 0%
4 virtual users
Home page 22.9 44.7 ms 60 ms 68.5 ms 0%
Post page 57.3 32.8 ms 45.8 ms 54.9 ms 0%
Tag page 11.5 28.9 ms 41.3 ms 48.1 ms 0%
Author page 11.4 28.5 ms 41.4 ms 46.7 ms 0%
RSS feed 11.4 31.1 ms 42.6 ms 48.2 ms 0%
16 virtual users
Home page 23.1 173 ms 226 ms 260 ms 0%
Post page 57.7 143 ms 190 ms 227 ms 0%
Tag page 11.5 97.5 ms 131 ms 149 ms 0%
Author page 11.5 95 ms 127 ms 148 ms 0%
RSS feed 11.5 98.5 ms 135 ms 153 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 8.58 15.5 ms 22 ms 26.8 ms 0%
Post editor 25.8 6.88 ms 9.86 ms 11.5 ms 0%
Saving a draft 25.8 17 ms 27 ms 69.3 ms 0%
Member list 8.6 17.9 ms 24.9 ms 30.2 ms 0%
4 virtual users
Post list 12.1 19.3 ms 26.9 ms 31 ms 0%
Post editor 36.4 9.84 ms 14.3 ms 16.8 ms 0%
Saving a draft 36.4 81.8 ms 116 ms 142 ms 0%
Member list 12.1 21.7 ms 31.5 ms 36.8 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 556 MB and MySQL at 625 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 3.07 40.5 ms 62.3 ms 70.3 ms 0%
Blog index 3.07 129 ms 176 ms 228 ms 0%
Blog post 9.19 14.4 ms 23.7 ms 30.5 ms 0%
Bread page 9.2 15.5 ms 22.3 ms 26.3 ms 0%
Location page 3.07 14.6 ms 21.5 ms 25.7 ms 0%
Site search 3.06 27.1 ms 45.3 ms 57.7 ms 0%
4 virtual users
Home page 4.97 115 ms 187 ms 230 ms 0%
Blog index 5 408 ms 623 ms 780 ms 0%
Blog post 14.9 29.6 ms 56.2 ms 76.8 ms 0%
Bread page 14.9 34.4 ms 58.4 ms 70.5 ms 0%
Location page 5 31.1 ms 56.9 ms 160 ms 0%
Site search 4.97 44.1 ms 111 ms 160 ms 0%
16 virtual users
Home page 6.21 298 ms 450 ms 532 ms 0%
Blog index 6.26 775 ms 1.04 s 1.2 s 0%
Blog post 18.6 164 ms 288 ms 359 ms 0%
Bread page 18.6 165 ms 305 ms 365 ms 0%
Location page 6.24 159 ms 271 ms 349 ms 0%
Site search 6.21 199 ms 325 ms 406 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 1.44 44.9 ms 57.6 ms 79.6 ms 0%
Page explorer 2.92 151 ms 207 ms 318 ms 0%
Page editor 4.35 77.7 ms 103 ms 233 ms 0%
Image library 1.44 30.8 ms 37.3 ms 109 ms 0%
Admin page search 1.44 19.9 ms 39.6 ms 44.3 ms 0%
4 virtual users
Admin dashboard 2.16 160 ms 355 ms 388 ms 0%
Page explorer 4.36 409 ms 695 ms 778 ms 0%
Page editor 6.57 208 ms 438 ms 537 ms 0%
Image library 2.21 127 ms 330 ms 413 ms 0%
Admin page search 2.16 50.4 ms 248 ms 329 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 309 MB, Postgres at 151 MB, and Redis at 25 MB.

Advertised vs. measured

Advertised Measured
vCPU 4 4
CPU Shared vCPU 2% of busy CPU time stolen
RAM 8 GB 7.7 GiB
Storage 100 GB NVMe 98.3 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 9575F 64-Core Processor
CPU cores
4
CPU frequency
3295 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
7.7 GiB
Swap reported
0 MiB
Disk reported
98.3 GiB
Virtualization reported
KVM
CPU steal
2% of busy CPU time stolen
Distro
Ubuntu 24.04.4 LTS
Kernel
6.8.0-137-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
Premium 4 vCPU / 8 GB
Product line
Premium
Location
Chicago #1
vCPU
4 shared vCPU
Architecture
x86_64
RAM
8 GB
Storage
100 GB NVMe
Virtualization
KVM
Network
Unknown
Transfer
5.12 TB
Port 25
Unknown
Monthly price at test time
€54.00 EUR
Hourly price at test time
€0.080 EUR
YABS version
v2026-09-20
Ran at
Oct 16, 2026, 17:55:33 UTC
Parser version
5

Run timeline

Queued
Oct 16, 2026, 17:54:00 UTC
First update from the server
Oct 16, 2026, 17:55:28 UTC
Completed
Oct 16, 2026, 19:24:00 UTC
Server deleted
Oct 16, 2026, 19:24:00 UTC
Cost of this run
€0.12 EUR
Watch party 0 watching

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

Watch party

Loading the party