Skip to main content

Togglebox 4 vCPU / 4 GB / 80 GB

Dallas

Benchmark complete
Finished Oct 11, 2026
Geekbench 7 single-core
1,015
Faster than 31% of 4 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
190,892
fio random read and write, 50/50
Monthly price at test time
$33.77
Same price today

Server

  • Provider
    Togglebox
  • Plan
    4 vCPU / 4 GB / 80 GB
  • Location
    Dallas
  • vCPU
    4
  • RAM
    4 GB
  • Storage
    80 GB NVMe
  • Network
    1 Gbps
  • OS image
    Ubuntu 24.04
  • Trigger
    Manual
  • Queued at
    Oct 11, 2026, 18:09:24 UTC
Visit Togglebox

CPU

Version Single-core Multi-core
Geekbench 7 1,015 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
1,031
83rd of 106
Single-core only
Navigation
1,306
58th of 106
Single-core only
HTML5 Browser
945
82nd of 106
Single-core only
PDF Viewer
1,115
75th of 106
Single-core only
Photo Library
844
82nd of 106
Single-core only
Clang
1,092
70th of 106
Single-core only
Text Processing
1,061
66th of 106
Single-core only
Asset Compression
821
95th of 106
Single-core only
HDR
931
75th of 106
Single-core only
Photo Editor
1,036
77th of 106
Single-core only
Ray Tracer
1,079
72nd of 106
Single-core only
Structure from Motion
1,174
73rd of 106
Single-core only
Game Physics
1,007
79th of 106
Single-core only
Video Encoder
979
78th of 106
Single-core only
Audio Encoder
984
83rd of 106
Single-core only
Video Player
934
83rd of 106
Single-core only

Rank among the 106 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 39.1 GB/s 3 1.14%
Scale higher is better 35.3 GB/s 3 1.29%
Add higher is better 38.5 GB/s 3 0.97%
Triad higher is better 39.8 GB/s 3 1.14%

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 893/s 3 3.69%
RSA 4096 verifies higher is better 58,832/s 3 0.934%
SHA-256 higher is better 1.03 GB/s 3 1.48%
AES-256-GCM higher is better 13.7 GB/s 3 0.252%
ChaCha20-Poly1305 higher is better 6.49 GB/s 3 0.347%

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 4.07 ms 3 0.3%
Requests per second, 90th percentile higher is better 964/s 3 1.18%
Request latency, 99.9th percentile lower is better 7.41 ms 3 2.94%
Requests per second, average higher is better 955/s 3 1.6%

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

Disk

Block size Read Write Total
4K 372.3 MB/s (95,320 IOPS) 373.3 MB/s (95,572 IOPS) 745.7 MB/s (190,892 IOPS)
64K 1.46 GB/s (23,925 IOPS) 1.47 GB/s (24,051 IOPS) 2.93 GB/s (47,976 IOPS)
512K 1.34 GB/s (2,738 IOPS) 1.41 GB/s (2,884 IOPS) 2.75 GB/s (5,622 IOPS)
1M 1.31 GB/s (1,346 IOPS) 1.4 GB/s (1,436 IOPS) 2.72 GB/s (2,782 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 1.4 Gbps 1.06 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.42 Gbps 1.37 Gbps
Leaseweb, Singapore, SG (10G) IPv4 932 Mbps 1.13 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.49 Gbps 1.43 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.47 Gbps 1.37 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 4,143 0.241 ms
fdatasync 2,842 0.352 ms
fsync 2,014 0.496 ms
fsync_writethrough Not supported here n/a
open_sync 2,077 0.481 ms
Two 8 kB writes
open_datasync 1,008 0.992 ms
fdatasync 3,367 0.297 ms
fsync 1,424 0.702 ms
fsync_writethrough Not supported here n/a
open_sync 1,166 0.857 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,459 0.685 ms
2 * 8kB open_sync writes 968 1.03 ms
4 * 4kB open_sync writes 828 1.21 ms
8 * 2kB open_sync writes 388 2.58 ms
16 * 1kB open_sync writes 152 6.59 ms
fsync on a non-write descriptor
write, fsync, close 1,813 0.552 ms
write, close, fsync 1,587 0.63 ms
Non-synced 8 kB writes
write 817,649 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 1,608 0.546 ms 1.05 ms 1.84 ms 3.03 ms 0
Read/write (TPC-B like) 8 5,620 1.16 ms 2.93 ms 4.98 ms 11.3 ms 0
Read/write (TPC-B like) 32 6,831 3.44 ms 12.2 ms 21.6 ms 39.9 ms 0
Read only 1 24,628 0.038 ms 0.051 ms 0.058 ms 0.072 ms 0
Read only 8 91,333 0.083 ms 0.139 ms 0.168 ms 0.211 ms 0
Read only 32 98,245 0.299 ms 0.427 ms 0.532 ms 0.726 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.34 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 1,266 0.681 ms 1.33 ms 2.74 ms 5.28 ms 0
Read/write (TPC-B like) 8 4,651 1.42 ms 3.91 ms 6.38 ms 12.1 ms 0
Read/write (TPC-B like) 32 7,759 3.53 ms 7.61 ms 12.1 ms 25.6 ms 0
Read only 1 19,094 0.049 ms 0.067 ms 0.08 ms 0.244 ms 0
Read only 8 72,785 0.103 ms 0.183 ms 0.224 ms 0.441 ms 0
Read only 32 72,231 0.412 ms 0.62 ms 0.767 ms 1.19 ms 0

Scale 100 (10,000,000 accounts), loaded in 14.1 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 1 297 5,950 2.91 ms 5.67 ms 8.9 ms 0
Read/write 8 1,128 22,568 6.55 ms 11.7 ms 16.4 ms 0
Read/write 32 1,688 33,764 18.3 ms 28.7 ms 38.2 ms 0
Read only 1 935 14,953 1.04 ms 1.18 ms 1.73 ms 0
Read only 8 3,249 51,978 2.48 ms 3.62 ms 4.1 ms 0
Read only 32 2,889 46,229 11 ms 14.5 ms 16.1 ms 0

10 tables of 100,000 rows, loaded in 5.3 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 99,332 90,302 0.615 ms 1.22 ms 1.39 ms
1:1 set:get 95,940 47,970 0.639 ms 1.26 ms 1.45 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 1,013 3,790 5,304 589 ms
Express express-postgresjs 13,439 18,855 72,926 36.2 ms
Fastify fastify-postgres 12,975 19,361 83,030 39.2 ms
NestJS nestjs 7,934 9,144 38,868 72.5 ms
Nuxt nuxt 11,649 17,729 61,484 56.8 ms
FastAPI fastapi 6,145 7,835 35,593 343 ms
Django django-postgresql 2,429 2,786 5,825 175 ms
Rails rails 3,759 5,237 23,194 82.8 ms
Laravel laravel 1,406 1,482 2,672 194 ms
Symfony symfony 1,810 1,985 5,126 151 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 4.24 382 ms 497 ms 552 ms 0%
Shop page 4.24 485 ms 643 ms 691 ms 0%
Category page 4.24 326 ms 538 ms 644 ms 0%
Product page 4.24 348 ms 471 ms 517 ms 0%
Product search 4.24 316 ms 430 ms 456 ms 0%
32 virtual users
Home page 4.05 1.57 s 1.81 s 1.88 s 0%
Shop page 4.05 2 s 2.29 s 2.42 s 0%
Category page 4.05 1.52 s 2.1 s 2.2 s 0%
Product page 4.05 1.5 s 1.75 s 1.86 s 0%
Product search 4.05 1.36 s 1.56 s 1.65 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 8.12 401 ms 523 ms 570 ms 0%
Cart 8.12 332 ms 443 ms 466 ms 0%
Checkout 8.12 257 ms 346 ms 382 ms 0%
32 virtual users
Add to cart 7.75 1.55 s 1.8 s 1.91 s 0%
Cart 7.75 1.42 s 1.64 s 1.74 s 0%
Checkout 7.75 1.19 s 1.38 s 1.43 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 2.06 212 ms 249 ms 504 ms 0%
Topic JSON 1.04 110 ms 126 ms 132 ms 0%
Home page 1.04 192 ms 214 ms 348 ms 0%
Categories page 0.528 225 ms 243 ms 456 ms 0%
User activity page 0.512 131 ms 186 ms 289 ms 0%
4 virtual users
Topic page 7.41 238 ms 288 ms 507 ms 0%
Topic JSON 3.7 121 ms 150 ms 173 ms 0%
Home page 3.69 215 ms 296 ms 514 ms 0%
Categories page 1.86 247 ms 298 ms 519 ms 0%
User activity page 1.84 148 ms 199 ms 389 ms 0%
16 virtual users
Topic page 6.68 971 ms 1.31 s 1.76 s 0%
Topic JSON 3.33 710 ms 950 ms 1.32 s 0%
Home page 3.33 915 ms 1.18 s 1.52 s 0%
Categories page 1.67 981 ms 1.16 s 1.67 s 0%
User activity page 1.69 805 ms 968 ms 1.03 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 139 28.1 ms 58.5 ms 87.6 ms 0%
Topic JSON 69.5 25.9 ms 55.1 ms 83.5 ms 0%
Home page 69.5 28.2 ms 59.5 ms 90.7 ms 0%
Categories page 34.7 27.9 ms 59.3 ms 92.2 ms 0%
User activity page 34.8 169 ms 241 ms 391 ms 0%

k6 with a fixed number of virtual users, 60 to 62 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 1024 MB of Postgres shared buffers, what its installer picks for a 4 GB box. It added a 2 GB swapfile first, the way its installer does, and didn't need it. The container peaked at 2,714 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 8.14 36.1 ms 40 ms 49.8 ms 0%
Post page 20.3 18.4 ms 20.9 ms 27.6 ms 0%
Tag page 4.06 24.7 ms 28.3 ms 36.7 ms 0%
Author page 4.06 24.2 ms 26.6 ms 29.7 ms 0%
RSS feed 4.06 26 ms 33.7 ms 36.1 ms 0%
4 virtual users
Home page 9.77 106 ms 133 ms 145 ms 0%
Post page 24.4 76.2 ms 103 ms 114 ms 0%
Tag page 4.89 71 ms 96.2 ms 108 ms 0%
Author page 4.88 70.4 ms 100 ms 114 ms 0%
RSS feed 4.86 75.5 ms 99.5 ms 107 ms 0%
16 virtual users
Home page 9.52 436 ms 503 ms 556 ms 0%
Post page 23.7 354 ms 423 ms 463 ms 0%
Tag page 4.73 239 ms 291 ms 325 ms 0%
Author page 4.76 236 ms 287 ms 307 ms 0%
RSS feed 4.74 245 ms 297 ms 317 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 4.57 33.9 ms 38.9 ms 46.2 ms 0%
Post editor 13.8 12.3 ms 14.9 ms 17.7 ms 0%
Saving a draft 13.8 32.5 ms 39.3 ms 52.3 ms 0%
Member list 4.58 38.3 ms 43.9 ms 55.7 ms 0%
4 virtual users
Post list 5.81 45.9 ms 51.4 ms 56.3 ms 0%
Post editor 17.5 22.1 ms 27.7 ms 30 ms 0%
Saving a draft 17.5 166 ms 212 ms 227 ms 0%
Member list 5.84 49 ms 55.6 ms 59.8 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 305 MB and MySQL at 625 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.61 81.7 ms 87.1 ms 89.5 ms 0%
Blog index 1.6 282 ms 296 ms 307 ms 0%
Blog post 4.79 26.7 ms 40.2 ms 48.1 ms 0%
Bread page 4.81 29.5 ms 32.1 ms 33.4 ms 0%
Location page 1.6 27.8 ms 30.8 ms 33.9 ms 0%
Site search 1.6 45.9 ms 75 ms 76 ms 0%
4 virtual users
Home page 3.02 181 ms 267 ms 340 ms 0%
Blog index 3.07 677 ms 900 ms 942 ms 0%
Blog post 9.07 50.2 ms 83.6 ms 99.9 ms 0%
Bread page 9.12 54.3 ms 86.7 ms 98.1 ms 0%
Location page 3.07 51.4 ms 82.2 ms 221 ms 0%
Site search 3.01 83.3 ms 169 ms 198 ms 0%
16 virtual users
Home page 3.36 547 ms 720 ms 765 ms 0%
Blog index 3.39 1.49 s 1.76 s 1.93 s 0%
Blog post 10 308 ms 490 ms 553 ms 0%
Bread page 10.1 309 ms 486 ms 567 ms 0%
Location page 3.37 302 ms 492 ms 562 ms 0%
Site search 3.31 353 ms 572 ms 611 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.625 88.5 ms 98.2 ms 114 ms 0%
Page explorer 1.28 369 ms 405 ms 518 ms 0%
Page editor 1.91 172 ms 233 ms 315 ms 0%
Image library 0.641 68.1 ms 74.2 ms 624 ms 0%
Admin page search 0.625 36.2 ms 78.8 ms 82.1 ms 0%
4 virtual users
Admin dashboard 1.07 274 ms 546 ms 606 ms 0%
Page explorer 2.12 880 ms 1.52 s 2.19 s 0%
Page editor 3.21 406 ms 764 ms 921 ms 0%
Image library 1.07 223 ms 521 ms 602 ms 0%
Admin page search 1.07 101 ms 244 ms 314 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 192 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 4 4
CPU Shared vCPU 0% of busy CPU time stolen
RAM 4 GB 3.8 GiB
Storage 80 GB NVMe 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
Intel Core Processor (Broadwell, no TSX, IBRS)
CPU cores
4
CPU frequency
2500 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
3.8 GiB
Swap reported
0 MiB
Disk reported
77.4 GiB
Virtualization reported
KVM
CPU steal
0% of busy CPU time stolen
Distro
Ubuntu 24.04.3 LTS
Kernel
6.8.0-88-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
No

Advertised at test time

Plan
4 vCPU / 4 GB / 80 GB
Product line
Cloud VPS
Location
Dallas
vCPU
4 shared vCPU
Architecture
x86_64
RAM
4 GB
Storage
80 GB NVMe
Virtualization
KVM
Network
1 Gbps
Transfer
10 TB
Port 25
On request
Monthly price at test time
$33.77
Hourly price at test time
$0.050
YABS version
v2026-09-20
Ran at
Oct 11, 2026, 18:10:27 UTC
Parser version
5

Run timeline

Queued
Oct 11, 2026, 18:09:24 UTC
Server created
Oct 11, 2026, 18:10:24 UTC
First update from the server
Oct 11, 2026, 18:10:24 UTC
Completed
Oct 11, 2026, 19:41:00 UTC
Server deleted
Oct 11, 2026, 19:41:00 UTC
Cost of this run
$0.077
Watch party 0 watching

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

Watch party

Loading the party