Scaleway BASIC2-A4C-8G

Paris 1

Benchmark complete

Finished Oct 9, 2026

Geekbench 7 single-core

944

Geekbench 7 multi-core

3,362

Disk 4K IOPS

5,158

fio random read and write, 50/50

Monthly price at test time

€37.74 EUR

76 multi-core points per dollar

Same price today

Server

Scaleway BASIC2-A4C-8G

Provider

Scaleway
Plan

BASIC2-A4C-8G
Location

Paris 1
vCPU

4
RAM

8 GB
Storage
Network

400 Mbps
OS image

ubuntu_noble
Trigger

Scheduled
Queued at

Oct 9, 2026, 20:11:00 UTC

Visit Scaleway

CPU

Version	Single-core	Multi-core	Result link
Geekbench 7	944	3,362	Geekbench Browser

Scores from different Geekbench versions aren't comparable with each other. Charts only use Geekbench 7.

Memory, TLS and scheduler

Memory bandwidth (STREAM)

Test	Result	Runs	Spread
Copy higher is better	68.9 GB/s	3	4.98%
Scale higher is better	66.8 GB/s	3	3.28%
Add higher is better	66 GB/s	3	10.2%
Triad higher is better	67.5 GB/s	3	2.59%

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	196/s	3	0.308%
RSA 4096 verifies higher is better	16,016/s	3	0.286%
SHA-256 higher is better	2.9 GB/s	3	1.22%
AES-256-GCM higher is better	9.38 GB/s	3	0.793%
ChaCha20-Poly1305 higher is better	3.48 GB/s	3	0.111%

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	14.9 ms	3	0.124%
Requests per second, 90th percentile higher is better	265/s	3	0.435%
Request latency, 99.9th percentile lower is better	34.3 ms	3	12.6%
Requests per second, average higher is better	264/s	3	0.468%

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

Disk

Block size	Read	Write	Total
4K	10.1 MB/s (2,575 IOPS)	10.1 MB/s (2,583 IOPS)	20.2 MB/s (5,158 IOPS)
64K	119.3 MB/s (1,908 IOPS)	122.8 MB/s (1,965 IOPS)	242.1 MB/s (3,873 IOPS)
512K	113.2 MB/s (226 IOPS)	122.9 MB/s (245 IOPS)	236.1 MB/s (471 IOPS)
1M	110 MB/s (109 IOPS)	122.7 MB/s (122 IOPS)	232.7 MB/s (231 IOPS)

fio random read and write, 50/50, run by YABS against the boot disk.

Network

IPv4 transfer speed

Target	Protocol	Send	Receive
Clouvider, London, UK (10G)	IPv4	646 Mbps	7.97 Gbps
Eranium, Amsterdam, NL (100G)	IPv4	648 Mbps	10.8 Gbps
Leaseweb, Singapore, SG (10G)	IPv4	613 Mbps	1.42 Gbps
Clouvider, Los Angeles, CA, US (10G)	IPv4	609 Mbps	1.36 Gbps
Leaseweb, NYC, NY, US (10G)	IPv4	628 Mbps	3.11 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	893	1.12 ms
fdatasync	922	1.08 ms
fsync	348	2.87 ms
fsync_writethrough	Not supported here	n/a
open_sync	364	2.74 ms
Two 8 kB writes
open_datasync	430	2.33 ms
fdatasync	826	1.21 ms
fsync	325	3.08 ms
fsync_writethrough	Not supported here	n/a
open_sync	170	5.87 ms
open_sync at different write sizes
1 * 16kB open_sync write	351	2.85 ms
2 * 8kB open_sync writes	185	5.41 ms
4 * 4kB open_sync writes	92.8	10.8 ms
8 * 2kB open_sync writes	45.5	22 ms
16 * 1kB open_sync writes	22.2	45.1 ms
fsync on a non-write descriptor
write, fsync, close	360	2.78 ms
write, close, fsync	352	2.84 ms
Non-synced 8 kB writes
write	1,057,765	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
Read/write (TPC-B like)	1	434	2.11 ms	2.97 ms	4.22 ms	14.1 ms
Read/write (TPC-B like)	8	2,060	3.01 ms	7.7 ms	12.7 ms	55.4 ms
Read/write (TPC-B like)	32	3,136	6.49 ms	29.6 ms	57.8 ms	195 ms
Read only	1	20,701	0.041 ms	0.081 ms	0.121 ms	0.487 ms
Read only	8	70,099	0.104 ms	0.196 ms	0.248 ms	0.393 ms
Read only	32	71,913	0.409 ms	0.681 ms	0.831 ms	1.18 ms

Scale 10 (1,000,000 accounts), loaded in 2.69 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
Read/write (TPC-B like)	1	350	2.28 ms	3.27 ms	7.4 ms	87.9 ms
Read/write (TPC-B like)	8	1,897	2.77 ms	6.29 ms	24.6 ms	140 ms
Read/write (TPC-B like)	32	2,732	6.35 ms	42 ms	102 ms	481 ms
Read only	1	12,583	0.061 ms	0.13 ms	0.217 ms	0.614 ms
Read only	8	51,593	0.142 ms	0.262 ms	0.331 ms	0.747 ms
Read only	32	51,178	0.583 ms	0.955 ms	1.2 ms	2 ms

Scale 100 (10,000,000 accounts), loaded in 35.8 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
Read/write	1	84.7	1,694	10.1 ms	18.3 ms	45 ms
Read/write	8	445	8,907	11.9 ms	50.1 ms	119 ms
Read/write	32	734	14,673	33.1 ms	109 ms	193 ms
Read only	1	567	9,074	1.5 ms	3.13 ms	4.1 ms
Read only	8	2,276	36,421	3.43 ms	5 ms	6.55 ms
Read only	32	2,053	32,840	15.3 ms	19.6 ms	23.1 ms

10 tables of 100,000 rows, loaded in 14.1 s. 60 s per run, one connection per thread.

Redis

memtier

Mix	Operations/s	Hits/s	Median	p99	p99.9
1:10 set:get	90,719	82,471	0.679 ms	1.34 ms	1.61 ms
1:1 set:get	89,541	44,770	0.679 ms	1.34 ms	1.66 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	The results arrived but couldn't be read, so no numbers are shown.
Express	The results arrived but couldn't be read, so no numbers are shown.
Fastify	The results arrived but couldn't be read, so no numbers are shown.
NestJS	The results arrived but couldn't be read, so no numbers are shown.
Nuxt	The results arrived but couldn't be read, so no numbers are shown.
FastAPI	The results arrived but couldn't be read, so no numbers are shown.
Django	The results arrived but couldn't be read, so no numbers are shown.
Rails	The results arrived but couldn't be read, so no numbers are shown.
Laravel	The results arrived but couldn't be read, so no numbers are shown.
Symfony	The results arrived but couldn't be read, so no numbers are shown.

WooCommerce

Page mix

Step	Requests/s	Median	p95	p99	Error rate
8 virtual users
Home page	3.07	520 ms	645 ms	678 ms	0%
Shop page	3.07	695 ms	855 ms	921 ms	0%
Category page	3.07	446 ms	704 ms	794 ms	0%
Product page	3.07	480 ms	619 ms	638 ms	0%
Product search	3.07	407 ms	521 ms	552 ms	0%
32 virtual users
Home page	3.03	1.98 s	2.25 s	2.37 s	0%
Shop page	3.03	2.58 s	2.93 s	2.96 s	0%
Category page	3.03	2.07 s	2.66 s	2.76 s	0%
Product page	3.03	1.89 s	2.12 s	2.18 s	0%
Product search	3.03	1.71 s	1.93 s	2.06 s	0%

Cart and checkout

Step	Requests/s	Median	p95	p99	Error rate
8 virtual users
Add to cart	6	543 ms	695 ms	744 ms	0%
Cart	6	445 ms	556 ms	596 ms	0%
Checkout	6	348 ms	450 ms	487 ms	0%
32 virtual users
Add to cart	5.71	2.05 s	2.42 s	2.57 s	0%
Cart	5.71	1.88 s	2.19 s	2.26 s	0%
Checkout	5.71	1.51 s	1.77 s	1.87 s	0%

k6 with a fixed number of virtual users, 62 to 65 s per level. The error rate counts responses that weren't a 200.

Advertised vs. measured

Spec	Advertised	Measured
vCPU	4	4
CPU	Shared vCPU	0.2% of busy CPU time stolen
RAM	8 GB	7.7 GiB
Storage		8.9 GiB
Architecture	arm64	arm64
Virtualization	KVM	VM-OTHER

Guests usually report slightly less RAM and disk than advertised because of kernel reservations and filesystem overhead.

Detected hardware

CPU model: Neoverse-N1
CPU cores: 4
CPU frequency: Unknown
AES-NI: Yes
VM-x/AMD-V: No
RAM reported: 7.7 GiB
Swap reported: 0 MiB
Disk reported: 8.9 GiB
Virtualization reported: VM-OTHER
CPU steal: 0.2% of busy CPU time stolen
Distro: Ubuntu 24.04.5 LTS
Kernel: 6.8.0-142-generic
Architecture: arm64
IPv4 reachable: Yes
IPv6 reachable: No

Advertised at test time

Plan: BASIC2-A4C-8G
Product line: General Purpose
Location: Paris 1
vCPU: 4 shared vCPU
Architecture: arm64
RAM: 8 GB
Storage
Virtualization: KVM
Network: 400 Mbps
Transfer: Unmetered
Port 25: Unknown
Monthly price at test time: €37.74 EUR
Hourly price at test time: €0.052 EUR
YABS version: v2026-09-20
Ran at: Oct 9, 2026, 20:12:00 UTC
Parser version: 5

Run timeline

Queued: Oct 9, 2026, 20:11:00 UTC
First update from the server: Oct 9, 2026, 20:11:53 UTC
Completed: Oct 9, 2026, 21:32:00 UTC
Server deleted: Oct 9, 2026, 21:32:00 UTC
Cost of this run: €0.070 EUR

TestResultTimevs last run

File Compression Not run

Navigation Not run

HTML5 Browser Not run

PDF Viewer Not run

Photo Library Not run

Clang Not run

Text Processing Not run

Asset Compression Not run

HDR Not run

Photo Editor Not run

Ray Tracer Not run

Structure from Motion Not run

Game Physics Not run

Video Encoder Not run

Audio Encoder Not run

Video Player Not run

TestResultTimevs last run

Watch party 0 watching

This party closed at 21:24 UTC. It's read only now.

Loading the party

RackCensus

Server

CPU

Memory, TLS and scheduler

Memory bandwidth (STREAM)

TLS and crypto (OpenSSL)

Scheduler latency (schbench)

Disk

Network

IPv4 transfer speed

Datastores

PostgreSQL

fsync speed (pg_test_fsync)

pgbench at scale 10

pgbench at scale 100

MySQL

sysbench OLTP

Redis

memtier

Web frameworks

WooCommerce

Page mix

Cart and checkout

Advertised vs. measured

Detected hardware

Advertised at test time

Run timeline

Watch party