Skip to main content

UpCloud Starter 4 vCPU / 8 GB

New York #1

Benchmark complete
Finished Oct 17, 2026
Geekbench 7 single-core
1,276
Faster than 70% of 4 vCPU plans
Geekbench 7 multi-core
4,390
Faster than 70% of 4 vCPU plans
Disk 4K IOPS
8,044
fio random read and write, 50/50
Monthly price at test time
€24.00 EUR
156 multi-core points per dollar
Same price today

Server

  • Provider
    UpCloud
  • Plan
    Starter 4 vCPU / 8 GB
  • Location
    New York #1
  • vCPU
    4
  • RAM
    8 GB
  • Storage
    40 GB
  • Network
    Unknown
  • OS image
    01000000-0000-4000-8000-000030240200
  • Trigger
    Scheduled
  • Queued at
    Oct 17, 2026, 20:30:00 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 1,276 4,390 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
1,423
88th of 241
4,208
33rd of 166
Navigation
1,495
70th of 241
Single-core only
HTML5 Browser
1,168
117th of 241
Single-core only
PDF Viewer
1,337
112th of 241
Single-core only
Photo Library
1,135
115th of 241
4,335
39th of 166
Clang
1,181
92nd of 241
4,726
35th of 166
Text Processing
1,102
115th of 241
3,867
47th of 166
Asset Compression
1,244
118th of 241
4,868
45th of 166
HDR
1,019
132nd of 241
3,213
53rd of 166
Photo Editor
1,407
110th of 241
5,240
27th of 166
Ray Tracer
1,368
78th of 241
5,050
41st of 166
Structure from Motion
1,423
103rd of 241
Single-core only
Game Physics
1,337
81st of 241
Single-core only
Video Encoder
1,189
113th of 241
Single-core only
Audio Encoder
1,317
103rd of 241
Single-core only
Video Player
1,376
103rd of 241
Single-core only

Rank among the 241 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 69.4 GB/s 3 32.3%
Scale higher is better 54.9 GB/s 3 28%
Add higher is better 54.6 GB/s 3 29.5%
Triad higher is better 56.3 GB/s 3 30.5%

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 905/s 3 0.475%
RSA 4096 verifies higher is better 58,992/s 3 0.983%
SHA-256 higher is better 2.71 GB/s 3 0.334%
AES-256-GCM higher is better 13.8 GB/s 3 0.35%
ChaCha20-Poly1305 higher is better 6.96 GB/s 3 0.135%

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 4.2 ms 3 0.381%
Requests per second, 90th percentile higher is better 916/s 3 0.702%
Request latency, 99.9th percentile lower is better 9.1 ms 3 1.83%
Requests per second, average higher is better 899/s 3 0.529%

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

Disk

Block size Read Write Total
4K 15.7 MB/s (4,020 IOPS) 15.7 MB/s (4,024 IOPS) 31.4 MB/s (8,044 IOPS)
64K 399.1 MB/s (6,385 IOPS) 401.2 MB/s (6,419 IOPS) 800.3 MB/s (12,804 IOPS)
512K 382.6 MB/s (765 IOPS) 403 MB/s (805 IOPS) 785.6 MB/s (1,570 IOPS)
1M 379.1 MB/s (379 IOPS) 404.4 MB/s (404 IOPS) 783.5 MB/s (783 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 975 Mbps 953 Mbps
Eranium, Amsterdam, NL (100G) IPv4 1.01 Gbps 1.02 Gbps
Leaseweb, Singapore, SG (10G) IPv4 632 Mbps 859 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.02 Gbps 1.03 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.07 Gbps 1.07 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 2,915 0.343 ms
fdatasync 3,018 0.331 ms
fsync 1,372 0.729 ms
fsync_writethrough Not supported here n/a
open_sync 1,431 0.699 ms
Two 8 kB writes
open_datasync 1,570 0.637 ms
fdatasync 2,699 0.371 ms
fsync 1,361 0.735 ms
fsync_writethrough Not supported here n/a
open_sync 791 1.27 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,386 0.721 ms
2 * 8kB open_sync writes 659 1.52 ms
4 * 4kB open_sync writes 386 2.59 ms
8 * 2kB open_sync writes 200 4.99 ms
16 * 1kB open_sync writes 99.2 10.1 ms
fsync on a non-write descriptor
write, fsync, close 1,344 0.744 ms
write, close, fsync 1,392 0.719 ms
Non-synced 8 kB writes
write 526,324 0.002 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 1,023 0.706 ms 1.83 ms 4.13 ms 23.6 ms 0
Read/write (TPC-B like) 8 5,549 1.17 ms 2.56 ms 4.43 ms 26.4 ms 0
Read/write (TPC-B like) 32 5,627 3.92 ms 14.5 ms 27.8 ms 67.6 ms 0
Read only 1 21,702 0.043 ms 0.059 ms 0.072 ms 0.097 ms 0
Read only 8 86,095 0.085 ms 0.151 ms 0.187 ms 0.25 ms 0
Read only 32 97,480 0.275 ms 0.464 ms 0.56 ms 0.843 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.43 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 1,111 0.758 ms 1.03 ms 2.48 ms 13.9 ms 0
Read/write (TPC-B like) 8 3,697 1.32 ms 2.71 ms 14.3 ms 90 ms 0
Read/write (TPC-B like) 32 4,830 3.73 ms 9.85 ms 87.4 ms 157 ms 0
Read only 1 14,743 0.053 ms 0.074 ms 0.09 ms 0.133 ms 0
Read only 8 66,358 0.11 ms 0.195 ms 0.241 ms 0.472 ms 0
Read only 32 75,688 0.38 ms 0.586 ms 0.743 ms 1.4 ms 0

Scale 100 (10,000,000 accounts), loaded in 16.7 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 1 269 5,384 3.3 ms 4.91 ms 12.5 ms 0
Read/write 8 926 18,516 6.67 ms 14.7 ms 77.2 ms 0
Read/write 32 1,284 25,689 21.5 ms 56.8 ms 83 ms 0
Read only 1 841 13,449 1.16 ms 1.42 ms 1.86 ms 0
Read only 8 3,474 55,579 2.26 ms 2.86 ms 3.62 ms 0
Read only 32 3,281 52,489 9.56 ms 12.1 ms 14.5 ms 0

10 tables of 100,000 rows, loaded in 5.9 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 59,381 53,982 1.06 ms 2.08 ms 2.3 ms
1:1 set:get 58,623 29,311 1.06 ms 2.11 ms 2.3 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 1,318 4,978 6,827 366 ms
Express express-postgresjs 16,280 22,231 58,706 33.7 ms
Fastify fastify-postgres 15,834 22,874 58,933 35.6 ms
NestJS nestjs 9,857 11,322 39,687 50.9 ms
Nuxt nuxt 14,089 21,481 58,505 47.9 ms
FastAPI fastapi 7,663 9,394 32,772 106 ms
Django django-postgresql 3,819 4,419 10,533 112 ms
Rails rails 5,753 7,926 30,273 61 ms
Laravel laravel 1,574 1,677 3,465 181 ms
Symfony symfony 2,074 2,210 6,494 134 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 4.75 336 ms 448 ms 494 ms 0%
Shop page 4.75 442 ms 571 ms 620 ms 0%
Category page 4.75 300 ms 481 ms 530 ms 0%
Product page 4.75 319 ms 411 ms 452 ms 0%
Product search 4.75 267 ms 358 ms 402 ms 0%
32 virtual users
Home page 4.51 1.36 s 1.55 s 1.67 s 0%
Shop page 4.51 1.74 s 2 s 2.05 s 0%
Category page 4.51 1.39 s 1.75 s 1.94 s 0%
Product page 4.51 1.31 s 1.48 s 1.54 s 0%
Product search 4.51 1.2 s 1.34 s 1.39 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 8.95 355 ms 459 ms 489 ms 0%
Cart 8.95 302 ms 393 ms 434 ms 0%
Checkout 8.95 244 ms 315 ms 334 ms 0%
32 virtual users
Add to cart 8.57 1.37 s 1.62 s 1.75 s 0%
Cart 8.57 1.28 s 1.5 s 1.61 s 0%
Checkout 8.57 1.05 s 1.27 s 1.33 s 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 2.4 184 ms 264 ms 471 ms 0%
Topic JSON 1.21 93.8 ms 107 ms 152 ms 0%
Home page 1.21 161 ms 184 ms 308 ms 0%
Categories page 0.613 190 ms 214 ms 239 ms 0%
User activity page 0.597 114 ms 136 ms 191 ms 0%
4 virtual users
Topic page 8 213 ms 325 ms 515 ms 0%
Topic JSON 4 108 ms 169 ms 307 ms 0%
Home page 3.98 193 ms 289 ms 518 ms 0%
Categories page 2.02 215 ms 310 ms 410 ms 0%
User activity page 1.98 142 ms 272 ms 377 ms 0%
16 virtual users
Topic page 8 823 ms 1.08 s 1.42 s 0%
Topic JSON 4.03 614 ms 842 ms 1.1 s 0%
Home page 4 777 ms 1.06 s 1.49 s 0%
Categories page 2 826 ms 1.07 s 1.35 s 0%
User activity page 2.02 670 ms 822 ms 993 ms 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 168 24.3 ms 44.6 ms 65.9 ms 0%
Topic JSON 83.9 22.5 ms 43 ms 65.7 ms 0%
Home page 83.9 24.3 ms 43.8 ms 64 ms 0%
Categories page 41.9 24.1 ms 45.4 ms 69.5 ms 0%
User activity page 42 140 ms 184 ms 306 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 2,794 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 10.2 29 ms 32.7 ms 37.4 ms 0%
Post page 25.5 14.8 ms 17.5 ms 21.9 ms 0%
Tag page 5.1 19.4 ms 22.1 ms 23.8 ms 0%
Author page 5.1 19.5 ms 22.2 ms 24.8 ms 0%
RSS feed 5.1 21.3 ms 26.1 ms 29.8 ms 0%
4 virtual users
Home page 12 87.6 ms 107 ms 119 ms 0%
Post page 29.9 62 ms 83.5 ms 94 ms 0%
Tag page 5.98 58.9 ms 79.9 ms 86.2 ms 0%
Author page 5.99 57.5 ms 79.1 ms 86.2 ms 0%
RSS feed 5.99 64.1 ms 84 ms 88.2 ms 0%
16 virtual users
Home page 12 349 ms 405 ms 431 ms 0%
Post page 30 275 ms 337 ms 361 ms 0%
Tag page 5.99 194 ms 249 ms 302 ms 0%
Author page 6.01 191 ms 251 ms 293 ms 0%
RSS feed 6.01 194 ms 244 ms 257 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 5.6 28.5 ms 32.6 ms 37 ms 0%
Post editor 16.8 9.61 ms 12.4 ms 15 ms 0%
Saving a draft 16.8 25.8 ms 31.9 ms 49 ms 0%
Member list 5.61 34.3 ms 40.5 ms 47.5 ms 0%
4 virtual users
Post list 7.09 34.8 ms 40.2 ms 43.3 ms 0%
Post editor 21.3 16.2 ms 20.5 ms 22.7 ms 0%
Saving a draft 21.3 142 ms 177 ms 195 ms 0%
Member list 7.09 44.4 ms 49.3 ms 52.6 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 538 MB and MySQL at 625 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.91 70 ms 76 ms 82.7 ms 0%
Blog index 1.91 230 ms 249 ms 256 ms 0%
Blog post 5.72 22.8 ms 34.7 ms 37 ms 0%
Bread page 5.72 25.3 ms 28.1 ms 30.1 ms 0%
Location page 1.91 24.1 ms 27.2 ms 31.8 ms 0%
Site search 1.91 37.9 ms 63.8 ms 69.7 ms 0%
4 virtual users
Home page 3.01 195 ms 290 ms 305 ms 0%
Blog index 3.03 654 ms 1 s 1.1 s 0%
Blog post 9.03 52.3 ms 92 ms 125 ms 0%
Bread page 9.05 59 ms 92.5 ms 109 ms 0%
Location page 3.03 55.8 ms 89.7 ms 93.9 ms 0%
Site search 3.01 79.6 ms 164 ms 217 ms 0%
16 virtual users
Home page 3.39 549 ms 736 ms 819 ms 0%
Blog index 3.44 1.46 s 1.7 s 1.81 s 0%
Blog post 10.1 302 ms 540 ms 721 ms 0%
Bread page 10.2 303 ms 521 ms 690 ms 0%
Location page 3.44 297 ms 494 ms 562 ms 0%
Site search 3.34 359 ms 521 ms 657 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.711 74.2 ms 87 ms 163 ms 0%
Page explorer 1.44 332 ms 372 ms 461 ms 0%
Page editor 2.15 157 ms 201 ms 283 ms 0%
Image library 0.711 57.6 ms 66.7 ms 521 ms 0%
Admin page search 0.711 31.4 ms 68.8 ms 84.5 ms 0%
4 virtual users
Admin dashboard 1.13 255 ms 523 ms 590 ms 0%
Page explorer 2.28 858 ms 1.26 s 1.58 s 0%
Page editor 3.39 387 ms 774 ms 851 ms 0%
Image library 1.13 198 ms 519 ms 571 ms 0%
Admin page search 1.13 93.1 ms 330 ms 441 ms 0%

k6 with a fixed number of virtual users, 60 to 61 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 299 MB, Postgres at 151 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 4 4
CPU Shared vCPU 0% of busy CPU time stolen
RAM 8 GB 7.7 GiB
Storage 40 GB 39.3 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 7542 32-Core Processor
CPU cores
4
CPU frequency
2895 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
7.7 GiB
Swap reported
0 MiB
Disk reported
39.3 GiB
Virtualization reported
KVM
CPU steal
0% 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
Starter 4 vCPU / 8 GB
Product line
Starter
Location
New York #1
vCPU
4 shared vCPU
Architecture
x86_64
RAM
8 GB
Storage
40 GB
Virtualization
KVM
Network
Unknown
Transfer
2.05 TB
Port 25
Unknown
Monthly price at test time
€24.00 EUR
Hourly price at test time
€0.036 EUR
YABS version
v2026-09-20
Ran at
Oct 17, 2026, 20:31:13 UTC
Parser version
5

Run timeline

Queued
Oct 17, 2026, 20:30:00 UTC
Server created
Oct 17, 2026, 20:31:07 UTC
First update from the server
Oct 17, 2026, 20:31:07 UTC
Completed
Oct 17, 2026, 22:04:59 UTC
Server deleted
Oct 17, 2026, 22:04:59 UTC
Cost of this run
€0.057 EUR
Watch party 0 watching

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

Watch party

Loading the party