Skip to main content

Kamatera 6T 6GB 100GB

Atlanta

Benchmark complete
Finished Oct 16, 2026
Geekbench 7 single-core
1,246
Geekbench 7 multi-core
5,715
Disk 4K IOPS
87,555
fio random read and write, 50/50
Monthly price at test time
$56.00
102 multi-core points per dollar
Same price today

Server

  • Provider
    Kamatera
  • Plan
    6T 6GB 100GB
  • Location
    Atlanta
  • vCPU
    6
  • RAM
    6 GB
  • Storage
    100 GB SSD
  • Network
    Unknown
  • OS image
    ubuntu_server_24.04_64-bit
  • Trigger
    Scheduled
  • Queued at
    Oct 16, 2026, 19:53:00 UTC
Visit Kamatera

CPU

Version Single-core Multi-core
Geekbench 7 1,246 5,715 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
1,297
107th of 216
1,898
101st of 147
Navigation
1,136
141st of 216
Single-core only
HTML5 Browser
1,292
80th of 216
Single-core only
PDF Viewer
1,489
68th of 216
Single-core only
Photo Library
1,225
89th of 216
6,681
18th of 147
Clang
1,182
82nd of 216
6,659
18th of 147
Text Processing
1,284
72nd of 216
6,269
17th of 147
Asset Compression
1,504
58th of 216
8,453
15th of 147
HDR
1,146
100th of 216
5,459
15th of 147
Photo Editor
1,419
96th of 216
6,426
13th of 147
Ray Tracer
1,083
125th of 216
7,246
19th of 147
Structure from Motion
1,413
93rd of 216
Single-core only
Game Physics
1,155
116th of 216
Single-core only
Video Encoder
1,045
127th of 216
Single-core only
Audio Encoder
1,177
125th of 216
Single-core only
Video Player
1,207
117th 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 91.5 GB/s 3 2.16%
Scale higher is better 59.4 GB/s 3 2.43%
Add higher is better 72.2 GB/s 3 1.2%
Triad higher is better 74.9 GB/s 3 1.77%

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 3,012/s 3 0.317%
RSA 4096 verifies higher is better 83,612/s 3 1.35%
SHA-256 higher is better 4.87 GB/s 3 0.802%
AES-256-GCM higher is better 69.5 GB/s 3 0.916%
ChaCha20-Poly1305 higher is better 20.2 GB/s 3 1.11%

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 2.56 ms 3 0.477%
Requests per second, 90th percentile higher is better 1,917/s 3 1.07%
Request latency, 99.9th percentile lower is better 5.76 ms 3 2.64%
Requests per second, average higher is better 1,852/s 3 0.738%

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

Disk

Block size Read Write Total
4K 170.8 MB/s (43,720 IOPS) 171.2 MB/s (43,835 IOPS) 342 MB/s (87,555 IOPS)
64K 1.75 GB/s (28,693 IOPS) 1.76 GB/s (28,844 IOPS) 3.51 GB/s (57,537 IOPS)
512K 3.99 GB/s (8,176 IOPS) 4.2 GB/s (8,610 IOPS) 8.2 GB/s (16,786 IOPS)
1M 7.33 GB/s (7,507 IOPS) 7.82 GB/s (8,007 IOPS) 15.15 GB/s (15,514 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 1.61 Gbps 2.44 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.74 Gbps 2.41 Gbps
Leaseweb, Singapore, SG (10G) IPv4 900 Mbps 1.06 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 2.89 Gbps 4.64 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 8.84 Gbps 6.35 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 6,989 0.143 ms
fdatasync 6,141 0.163 ms
fsync 4,329 0.231 ms
fsync_writethrough Not supported here n/a
open_sync 4,693 0.213 ms
Two 8 kB writes
open_datasync 3,524 0.284 ms
fdatasync 6,279 0.159 ms
fsync 4,246 0.236 ms
fsync_writethrough Not supported here n/a
open_sync 2,218 0.451 ms
open_sync at different write sizes
1 * 16kB open_sync write 4,874 0.205 ms
2 * 8kB open_sync writes 2,397 0.417 ms
4 * 4kB open_sync writes 1,140 0.877 ms
8 * 2kB open_sync writes 625 1.6 ms
16 * 1kB open_sync writes 294 3.41 ms
fsync on a non-write descriptor
write, fsync, close 4,170 0.24 ms
write, close, fsync 3,997 0.25 ms
Non-synced 8 kB writes
write 1,592,594 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 1,368 0.642 ms 1.21 ms 2.21 ms 5.05 ms 0
Read/write (TPC-B like) 8 7,217 0.934 ms 2.16 ms 3.97 ms 7.54 ms 0
Read/write (TPC-B like) 32 9,226 2.38 ms 9.35 ms 16.5 ms 35 ms 0
Read only 1 18,305 0.047 ms 0.089 ms 0.164 ms 0.285 ms 0
Read only 8 259,216 0.023 ms 0.067 ms 0.093 ms 0.142 ms 0
Read only 32 214,193 0.132 ms 0.238 ms 0.308 ms 0.504 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.36 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 1,365 0.646 ms 1.15 ms 2.12 ms 4.8 ms 0
Read/write (TPC-B like) 8 7,181 0.919 ms 2.29 ms 4.99 ms 11 ms 0
Read/write (TPC-B like) 32 11,797 2.24 ms 5.52 ms 10.2 ms 19.6 ms 0
Read only 1 14,001 0.063 ms 0.117 ms 0.204 ms 0.33 ms 0
Read only 8 163,704 0.037 ms 0.106 ms 0.147 ms 0.278 ms 0
Read only 32 142,715 0.203 ms 0.361 ms 0.467 ms 1.06 ms 0

Scale 100 (10,000,000 accounts), loaded in 13 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 1 314 6,280 2.97 ms 4.65 ms 7.43 ms 0
Read/write 8 1,564 31,271 4.74 ms 8.74 ms 12.3 ms 0
Read/write 32 2,556 51,124 11.9 ms 21.1 ms 26.2 ms 0
Read only 1 708 11,333 1.34 ms 2.03 ms 2.52 ms 0
Read only 8 7,509 120,140 0.92 ms 2.03 ms 2.62 ms 0
Read only 32 7,694 123,105 3.89 ms 6.43 ms 7.99 ms 0

10 tables of 100,000 rows, loaded in 3.8 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 105,834 96,213 0.543 ms 1.22 ms 1.86 ms
1:1 set:get 105,087 52,543 0.559 ms 1.22 ms 1.75 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 1,523 5,719 7,799 301 ms
Express express-postgresjs 22,203 31,734 139,553 24.2 ms
Fastify fastify-postgres 21,502 33,703 161,808 24.7 ms
NestJS nestjs 14,783 16,826 101,441 41.6 ms
Nuxt nuxt 19,281 28,916 106,991 41.3 ms
FastAPI fastapi 11,652 15,871 66,902 69.1 ms
Django django-postgresql 5,106 5,736 19,674 113 ms
Rails rails 8,357 12,035 60,484 61 ms
Laravel laravel 1,986 2,017 3,645 160 ms
Symfony symfony 2,581 2,724 7,864 111 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 6.42 238 ms 364 ms 442 ms 0%
Shop page 6.42 313 ms 470 ms 528 ms 0%
Category page 6.42 213 ms 369 ms 453 ms 0%
Product page 6.42 225 ms 358 ms 422 ms 0%
Product search 6.42 186 ms 306 ms 343 ms 0%
32 virtual users
Home page 6.07 1.04 s 1.3 s 1.5 s 0%
Shop page 6.07 1.34 s 1.61 s 1.72 s 0%
Category page 6.07 944 ms 1.38 s 1.5 s 0%
Product page 6.07 975 ms 1.21 s 1.3 s 0%
Product search 6.07 868 ms 1.05 s 1.14 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 12.4 250 ms 346 ms 392 ms 0%
Cart 12.4 209 ms 289 ms 319 ms 0%
Checkout 12.4 160 ms 228 ms 254 ms 0%
32 virtual users
Add to cart 12.2 1.04 s 1.26 s 1.36 s 0%
Cart 12.2 872 ms 1.07 s 1.16 s 0%
Checkout 12.2 705 ms 891 ms 958 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 1.77 255 ms 310 ms 488 ms 0%
Topic JSON 0.892 129 ms 145 ms 147 ms 0%
Home page 0.892 220 ms 252 ms 270 ms 0%
Categories page 0.446 265 ms 437 ms 516 ms 0%
User activity page 0.446 159 ms 193 ms 207 ms 0%
4 virtual users
Topic page 6.49 269 ms 450 ms 619 ms 0%
Topic JSON 3.27 138 ms 179 ms 340 ms 0%
Home page 3.25 235 ms 344 ms 564 ms 0%
Categories page 1.65 274 ms 471 ms 547 ms 0%
User activity page 1.63 171 ms 213 ms 399 ms 0%
16 virtual users
Topic page 8.69 765 ms 1.08 s 1.42 s 0%
Topic JSON 4.33 564 ms 751 ms 797 ms 0%
Home page 4.31 708 ms 946 ms 1.18 s 0%
Categories page 2.21 757 ms 1 s 1.2 s 0%
User activity page 2.16 621 ms 808 ms 891 ms 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 175 21.9 ms 46.7 ms 71.7 ms 0%
Topic JSON 87.6 20.2 ms 44.7 ms 71.5 ms 0%
Home page 87.6 22 ms 47.6 ms 79 ms 0%
Categories page 43.8 21.6 ms 45.6 ms 69.8 ms 0%
User activity page 43.8 131 ms 206 ms 363 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 1536 MB of Postgres shared buffers, what its installer picks for a 6 GB box. Its installer adds no swap on a box this big. The container peaked at 2,631 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 7.58 35.4 ms 46.1 ms 51.7 ms 0%
Post page 18.9 21.8 ms 28.5 ms 33.3 ms 0%
Tag page 3.8 23.4 ms 31.9 ms 35.2 ms 0%
Author page 3.78 24 ms 33.2 ms 38.5 ms 0%
RSS feed 3.78 25.1 ms 34 ms 38.8 ms 0%
4 virtual users
Home page 10.1 104 ms 136 ms 153 ms 0%
Post page 25.3 74.1 ms 103 ms 120 ms 0%
Tag page 5.04 63.4 ms 85.1 ms 95.7 ms 0%
Author page 5.06 65.2 ms 88.7 ms 99 ms 0%
RSS feed 5.06 72.8 ms 103 ms 120 ms 0%
16 virtual users
Home page 9.95 403 ms 510 ms 577 ms 0%
Post page 24.9 336 ms 432 ms 498 ms 0%
Tag page 4.97 221 ms 296 ms 312 ms 0%
Author page 4.98 222 ms 288 ms 342 ms 0%
RSS feed 4.97 223 ms 302 ms 381 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 3.83 33.9 ms 43.4 ms 47.4 ms 0%
Post editor 11.5 16.4 ms 21.7 ms 26.1 ms 0%
Saving a draft 11.5 41.7 ms 52.6 ms 63.6 ms 0%
Member list 3.85 37.8 ms 52.1 ms 63.2 ms 0%
4 virtual users
Post list 5.48 44.3 ms 57.4 ms 64.6 ms 0%
Post editor 16.5 25.5 ms 35.3 ms 41 ms 0%
Saving a draft 16.5 181 ms 230 ms 261 ms 0%
Member list 5.51 49.9 ms 66.9 ms 73.4 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 522 MB and MySQL at 626 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.35 99.5 ms 115 ms 175 ms 0%
Blog index 1.35 336 ms 372 ms 399 ms 0%
Blog post 4.02 31.5 ms 48.9 ms 60.9 ms 0%
Bread page 4.02 34 ms 41.2 ms 47.3 ms 0%
Location page 1.35 31.8 ms 38.2 ms 42.8 ms 0%
Site search 1.35 51.2 ms 91.1 ms 97.7 ms 0%
4 virtual users
Home page 2.56 221 ms 347 ms 386 ms 0%
Blog index 2.58 747 ms 1.17 s 1.31 s 0%
Blog post 7.67 61.9 ms 113 ms 152 ms 0%
Bread page 7.71 62.9 ms 110 ms 269 ms 0%
Location page 2.6 56.1 ms 107 ms 126 ms 0%
Site search 2.55 88.2 ms 211 ms 252 ms 0%
16 virtual users
Home page 2.92 610 ms 859 ms 951 ms 0%
Blog index 3.02 1.67 s 2 s 2.23 s 0%
Blog post 8.81 346 ms 580 ms 729 ms 0%
Bread page 8.79 354 ms 612 ms 744 ms 0%
Location page 2.97 329 ms 582 ms 669 ms 0%
Site search 2.94 412 ms 685 ms 784 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.593 105 ms 132 ms 142 ms 0%
Page explorer 1.22 389 ms 467 ms 531 ms 0%
Page editor 1.79 180 ms 253 ms 435 ms 0%
Image library 0.593 72.3 ms 88.7 ms 690 ms 0%
Admin page search 0.593 42.4 ms 103 ms 208 ms 0%
4 virtual users
Admin dashboard 1.05 252 ms 603 ms 671 ms 0%
Page explorer 2.12 823 ms 1.8 s 2.7 s 0%
Page editor 3.17 419 ms 810 ms 935 ms 0%
Image library 1.05 266 ms 473 ms 578 ms 0%
Admin page search 1.05 90.9 ms 256 ms 389 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 296 MB, Postgres at 165 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 6 6
CPU Shared vCPU 0% of busy CPU time stolen
RAM 6 GB 5.8 GiB
Storage 100 GB SSD 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
Intel Xeon Processor (SapphireRapids)
CPU cores
6
CPU frequency
2700 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
5.8 GiB
Swap reported
0 MiB
Disk reported
98.3 GiB
Virtualization reported
KVM
CPU steal
0% of busy CPU time stolen
Distro
Ubuntu 24.04.5 LTS
Kernel
6.8.0-139-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
No

Advertised at test time

Plan
6T 6GB 100GB
Product line
Type T Burstable
Location
Atlanta
vCPU
6 shared vCPU
Architecture
x86_64
RAM
6 GB
Storage
100 GB SSD
Virtualization
KVM
Network
Unknown
Transfer
5 TB
Port 25
Unknown
Monthly price at test time
$56.00
Hourly price at test time
$0.077
YABS version
v2026-09-20
Ran at
Oct 16, 2026, 19:55:47 UTC
Parser version
5

Run timeline

Queued
Oct 16, 2026, 19:53:00 UTC
First update from the server
Oct 16, 2026, 19:55:41 UTC
Completed
Oct 16, 2026, 21:30:00 UTC
Server deleted
Oct 16, 2026, 21:30:00 UTC
Cost of this run
$0.12
Watch party 0 watching

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

Watch party

Loading the party