Skip to main content

Vultr High Performance AMD 2 vCPU / 2 GB

New Jersey, US

Benchmark complete
Finished Oct 17, 2026
Geekbench 7 single-core
1,373
Faster than 69% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
138,060
fio random read and write, 50/50
Monthly price at test time
$18.00
Same price today

Server

  • Provider
    Vultr
  • Plan
    High Performance AMD 2 vCPU / 2 GB
  • Location
    New Jersey, US
  • vCPU
    2
  • RAM
    2 GB
  • Storage
    60 GB NVMe
  • Network
    Unknown
  • OS image
    2284
  • Trigger
    Scheduled
  • Queued at
    Oct 17, 2026, 02:18:00 UTC
Visit Vultr

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 1,373 Skipped Geekbench Browser

Multi-core was skipped because Geekbench 7 needs about 3.1 GB of free memory to run 2 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
1,521
58th of 245
Single-core only
Navigation
1,430
86th of 245
Single-core only
HTML5 Browser
1,282
91st of 245
Single-core only
PDF Viewer
1,447
93rd of 245
Single-core only
Photo Library
1,285
87th of 245
Single-core only
Clang
1,269
75th of 245
Single-core only
Text Processing
1,085
122nd of 245
Single-core only
Asset Compression
1,410
90th of 245
Single-core only
HDR
1,511
64th of 245
Single-core only
Photo Editor
1,584
80th of 245
Single-core only
Ray Tracer
1,193
129th of 245
Single-core only
Structure from Motion
1,494
95th of 245
Single-core only
Game Physics
1,403
68th of 245
Single-core only
Video Encoder
1,365
76th of 245
Single-core only
Audio Encoder
1,396
94th of 245
Single-core only
Video Player
1,383
101st of 245
Single-core only

Rank among the 245 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 50.5 GB/s 3 10.5%
Scale higher is better 54.2 GB/s 3 25.2%
Add higher is better 50.3 GB/s 3 20.1%
Triad higher is better 48.6 GB/s 3 22.2%

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 310/s 3 4.26%
RSA 4096 verifies higher is better 20,059/s 3 3.51%
SHA-256 higher is better 1.62 GB/s 3 4.18%
AES-256-GCM higher is better 7.11 GB/s 3 4.08%
ChaCha20-Poly1305 higher is better 4.51 GB/s 3 0.755%

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 5.04 ms 3 1.02%
Requests per second, 90th percentile higher is better 376/s 3 0.935%
Request latency, 99.9th percentile lower is better 13.5 ms 3 4.68%
Requests per second, average higher is better 348/s 3 2.08%

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

Disk

Block size Read Write Total
4K 269.3 MB/s (68,939 IOPS) 270 MB/s (69,121 IOPS) 539.3 MB/s (138,060 IOPS)
64K 1.87 GB/s (30,658 IOPS) 1.88 GB/s (30,819 IOPS) 3.75 GB/s (61,477 IOPS)
512K 2.25 GB/s (4,602 IOPS) 2.37 GB/s (4,846 IOPS) 4.61 GB/s (9,448 IOPS)
1M 249.3 MB/s (249 IOPS) 265.9 MB/s (265 IOPS) 515.2 MB/s (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 2.38 Gbps 3.09 Gbps
Eranium, Amsterdam, NL (100G) IPv4 6.47 Gbps 4.34 Gbps
Leaseweb, Singapore, SG (10G) IPv4 1.86 Gbps 2.51 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 3.3 Gbps 849 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 8.42 Gbps 5.55 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 6,295 0.159 ms
fdatasync 5,509 0.182 ms
fsync 4,010 0.249 ms
fsync_writethrough Not supported here n/a
open_sync 4,053 0.247 ms
Two 8 kB writes
open_datasync 2,893 0.346 ms
fdatasync 5,450 0.183 ms
fsync 3,718 0.269 ms
fsync_writethrough Not supported here n/a
open_sync 2,047 0.489 ms
open_sync at different write sizes
1 * 16kB open_sync write 4,723 0.212 ms
2 * 8kB open_sync writes 2,317 0.432 ms
4 * 4kB open_sync writes 564 1.77 ms
8 * 2kB open_sync writes 548 1.82 ms
16 * 1kB open_sync writes 260 3.85 ms
fsync on a non-write descriptor
write, fsync, close 2,966 0.337 ms
write, close, fsync 3,487 0.287 ms
Non-synced 8 kB writes
write 548,985 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 1,491 0.525 ms 1.2 ms 3.58 ms 8.58 ms 0
Read/write (TPC-B like) 8 3,842 1.73 ms 4.09 ms 7.92 ms 18.3 ms 0
Read/write (TPC-B like) 32 3,864 6.16 ms 20.7 ms 37.7 ms 69.7 ms 0
Read only 1 23,157 0.035 ms 0.071 ms 0.144 ms 0.438 ms 0
Read only 8 49,622 0.134 ms 0.268 ms 0.411 ms 1.15 ms 0
Read only 32 49,154 0.479 ms 1.01 ms 1.56 ms 3.48 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.72 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) 1 965 0.826 ms 2.27 ms 5.7 ms 13.7 ms 0
Read/write (TPC-B like) 8 3,091 2.17 ms 5.04 ms 9.06 ms 16.6 ms 0
Read/write (TPC-B like) 32 3,140 8.63 ms 20.4 ms 31.5 ms 54 ms 0
Read only 1 3,552 0.246 ms 0.543 ms 1.69 ms 8.71 ms 0
Read only 8 24,200 0.206 ms 0.783 ms 1.89 ms 9.13 ms 0
Read only 32 29,528 0.805 ms 2.13 ms 4.01 ms 8.49 ms 0

Scale 100 (10,000,000 accounts), loaded in 16.6 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 1 318 6,359 2.62 ms 5.67 ms 12.5 ms 0
Read/write 8 738 14,761 9.91 ms 19 ms 37.6 ms 0
Read/write 32 808 16,161 37.6 ms 68.1 ms 92.4 ms 0
Read only 1 857 13,712 1.06 ms 1.7 ms 2.86 ms 0
Read only 8 1,603 25,651 4.65 ms 7.84 ms 10.1 ms 0
Read only 32 1,507 24,111 20.4 ms 30.3 ms 39.7 ms 0

10 tables of 100,000 rows, loaded in 10.9 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 56,985 51,804 0.663 ms 4.05 ms 6.14 ms
1:1 set:get 57,958 28,979 0.687 ms 3.66 ms 5.31 ms

1,000,000 keys of 32 bytes. 64 connections over 2 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 521 2,146 3,138 875 ms
Express express-postgresjs 6,876 9,906 33,852 73.3 ms
Fastify fastify-postgres 7,042 10,787 39,944 73.6 ms
NestJS nestjs 4,540 5,568 19,650 106 ms
Nuxt nuxt 6,067 9,545 30,040 84.7 ms
FastAPI fastapi 3,315 4,058 20,257 317 ms
Django django-postgresql 1,767 1,970 4,777 332 ms
Rails rails 2,659 3,592 13,827 134 ms
Laravel laravel 758 772 1,564 376 ms
Symfony symfony 956 946 2,864 387 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 2.07 770 ms 886 ms 928 ms 0%
Shop page 2.07 1.05 s 1.21 s 1.27 s 0%
Category page 2.07 643 ms 1.08 s 1.13 s 0%
Product page 2.07 694 ms 829 ms 943 ms 0%
Product search 2.07 603 ms 738 ms 826 ms 0%
32 virtual users
Home page 2.02 2.84 s 3.55 s 3.66 s 0%
Shop page 2.02 3.84 s 4.39 s 4.5 s 0%
Category page 2.02 3.3 s 4.05 s 4.36 s 0%
Product page 2.02 2.79 s 3.09 s 3.19 s 0%
Product search 2.02 2.68 s 2.96 s 3.08 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 3.7 874 ms 1.1 s 1.33 s 0%
Cart 3.7 708 ms 923 ms 1.07 s 0%
Checkout 3.7 543 ms 708 ms 789 ms 0%
32 virtual users
Add to cart 4.09 2.67 s 3.35 s 3.57 s 0%
Cart 4.09 2.83 s 3.2 s 3.29 s 0%
Checkout 4.09 2.2 s 2.59 s 2.73 s 0%

k6 with a fixed number of virtual users, 62 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 1.82 236 ms 391 ms 504 ms 0%
Topic JSON 0.908 118 ms 172 ms 313 ms 0%
Home page 0.908 202 ms 316 ms 532 ms 0%
Categories page 0.462 238 ms 391 ms 504 ms 0%
User activity page 0.446 147 ms 252 ms 362 ms 0%
4 virtual users
Topic page 3.53 493 ms 649 ms 1.54 s 0%
Topic JSON 1.76 262 ms 351 ms 401 ms 0%
Home page 1.76 439 ms 624 ms 913 ms 0%
Categories page 0.907 530 ms 724 ms 1.28 s 0%
User activity page 0.874 304 ms 446 ms 859 ms 0%
16 virtual users
Topic page 3.22 1.61 s 2.19 s 2.56 s 0%
Topic JSON 1.65 1.35 s 1.8 s 1.91 s 0%
Home page 1.64 1.56 s 2.1 s 2.53 s 0%
Categories page 0.81 1.59 s 2.19 s 2.43 s 0%
User activity page 0.826 1.44 s 1.71 s 1.94 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 66.3 69.8 ms 155 ms 223 ms 0%
Topic JSON 33.1 69.9 ms 160 ms 213 ms 0%
Home page 33.2 70.6 ms 157 ms 239 ms 0%
Categories page 16.6 71.2 ms 158 ms 225 ms 0%
User activity page 16.6 212 ms 346 ms 532 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 4 app workers and 256 MB of Postgres shared buffers, what its installer picks for a 2 GB box. It had swap the way its installer sets a box up and used up to 469 MB of it. The container peaked at 1,514 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 7.51 36.4 ms 50 ms 61 ms 0%
Post page 18.7 20.2 ms 30.4 ms 38.5 ms 0%
Tag page 3.75 24.8 ms 33.8 ms 42.7 ms 0%
Author page 3.75 24.3 ms 34.9 ms 43.3 ms 0%
RSS feed 3.75 30.1 ms 40.4 ms 50.9 ms 0%
4 virtual users
Home page 9.44 105 ms 150 ms 187 ms 0%
Post page 23.6 78 ms 121 ms 150 ms 0%
Tag page 4.73 69.6 ms 99.4 ms 128 ms 0%
Author page 4.71 69.5 ms 114 ms 138 ms 0%
RSS feed 4.71 75.3 ms 102 ms 152 ms 0%
16 virtual users
Home page 9.58 421 ms 521 ms 586 ms 0%
Post page 24 350 ms 451 ms 508 ms 0%
Tag page 4.78 231 ms 304 ms 352 ms 0%
Author page 4.78 228 ms 306 ms 356 ms 0%
RSS feed 4.78 234 ms 307 ms 355 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 4.42 33.1 ms 48.7 ms 57.4 ms 0%
Post editor 13.3 13 ms 20.6 ms 32.6 ms 0%
Saving a draft 13.3 32.3 ms 49 ms 59.4 ms 0%
Member list 4.42 37 ms 52.9 ms 59.9 ms 0%
4 virtual users
Post list 4.75 47 ms 73.8 ms 102 ms 0%
Post editor 14.2 24.4 ms 40.4 ms 63.5 ms 0%
Saving a draft 14.3 206 ms 306 ms 376 ms 0%
Member list 4.75 58 ms 96.6 ms 116 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 363 MB and MySQL at 583 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.53 86.5 ms 122 ms 148 ms 0%
Blog index 1.53 290 ms 372 ms 391 ms 0%
Blog post 4.54 26.9 ms 46.4 ms 55.9 ms 0%
Bread page 4.56 29.5 ms 42.4 ms 54.9 ms 0%
Location page 1.53 28.4 ms 37.7 ms 59.7 ms 0%
Site search 1.51 43 ms 85.5 ms 105 ms 0%
4 virtual users
Home page 2.87 202 ms 290 ms 340 ms 0%
Blog index 2.91 649 ms 924 ms 962 ms 0%
Blog post 8.62 55.7 ms 99.9 ms 127 ms 0%
Bread page 8.64 60.4 ms 91.2 ms 112 ms 0%
Location page 2.91 57.9 ms 88.2 ms 97.1 ms 0%
Site search 2.86 87.4 ms 180 ms 213 ms 0%
16 virtual users
Home page 3.1 604 ms 803 ms 863 ms 0%
Blog index 3.12 1.47 s 1.74 s 2.01 s 0%
Blog post 9.31 352 ms 545 ms 689 ms 0%
Bread page 9.37 349 ms 535 ms 620 ms 0%
Location page 3.13 347 ms 535 ms 599 ms 0%
Site search 3.1 434 ms 650 ms 776 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.596 96 ms 133 ms 147 ms 0%
Page explorer 1.21 385 ms 565 ms 697 ms 0%
Page editor 1.79 185 ms 284 ms 406 ms 0%
Image library 0.596 71.3 ms 143 ms 699 ms 0%
Admin page search 0.596 41.6 ms 82.7 ms 88.8 ms 0%
4 virtual users
Admin dashboard 1.05 221 ms 479 ms 521 ms 0%
Page explorer 2.13 967 ms 1.44 s 1.62 s 0%
Page editor 3.21 405 ms 774 ms 1 s 0%
Image library 1.08 209 ms 447 ms 558 ms 0%
Admin page search 1.05 103 ms 390 ms 471 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 298 MB, Postgres at 176 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 6.1% of busy CPU time stolen
RAM 2 GB 1.9 GiB
Storage 60 GB NVMe 56.2 GiB
Architecture x86_64 x86_64
Virtualization KVM MICROSOFT

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
2
CPU frequency
3250 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
1.9 GiB
Swap reported
5.8 GiB
Disk reported
56.2 GiB
Virtualization reported
MICROSOFT
CPU steal
6.1% of busy CPU time stolen
Distro
Ubuntu 24.04.5 LTS
Kernel
6.8.0-146-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
High Performance AMD 2 vCPU / 2 GB
Product line
Cloud Compute High Performance
Location
New Jersey, US
vCPU
2 shared vCPU
Architecture
x86_64
RAM
2 GB
Storage
60 GB NVMe
Virtualization
KVM
Network
Unknown
Transfer
4.1 TB
Port 25
On request
Monthly price at test time
$18.00
Hourly price at test time
$0.025
YABS version
v2026-09-20
Ran at
Oct 17, 2026, 02:21:32 UTC
Parser version
5

Run timeline

Queued
Oct 17, 2026, 02:18:00 UTC
Server created
Oct 17, 2026, 02:19:15 UTC
First update from the server
Oct 17, 2026, 02:19:15 UTC
Completed
Oct 17, 2026, 03:51:32 UTC
Server deleted
Oct 17, 2026, 03:51:32 UTC
Cost of this run
$0.039
Watch party 0 watching

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

Watch party

Loading the party