Reviewed measurements

Compare the evidence.

Two reports. The same workloads. Benchmark medians and separate network trials in view.

Selected plans
DigitalOceanc-4
Vultrvoc-c-4c-8gb-75s-amd
Different resources selected: 4 vCPU · 7.8 GiB / 4 vCPU · 7.7 GiBSource location: London, UK · same agent build and methodology.
CPU allocation
4 vCPU
4 vCPU
Observed memory
7.8 GiB
7.7 GiB
Processor
Intel Xeon Platinum 8280 @ 2.70GHz
AMD EPYC-Milan
Location
London, UKlon1
London, UKLHR
List price
$84.00 / month$0.125 / hour · before tax
$80.00 / month$0.110 / hour · before tax
OS / architecture
Ubuntu 24.04.5 LTS / x86_64
Ubuntu 24.04.5 LTS / x86_64
Sampling
1 deployment · 24h run skipped
1 deployment · 24h run skipped
Report date
17 Oct 2026
17 Oct 2026
Methodology
pilot-1 · AI-assisted review
pilot-1 · AI-assisted review
Each column is one deployment. Matching context does not establish equivalent physical hosts.Benchmark medians · network trials linked separately
PerformanceReviewed data
DigitalOcean4 vCPU · 7.8 GiB
Vultr4 vCPU · 7.7 GiB
01 /

CPU performance

sysbench prime events · max prime 20,000 · gzip level 6 · higher is better

MetricDigitalOcean c-4Vultr voc-c-4c-8gb-75s-amd
Single thread
458.3events/s23% of 2,000
1,671events/s84% of 2,000
All 4 vCPUs
1,435events/s18% of 8,000
6,656events/s83% of 8,000
gzip compression
207.0MiB/s83% of 250
242.1MiB/s97% of 250

Identical thread counts and test settings. Bars use a common scale within each row.

02 /

Memory bandwidth

sysbench · 256 MiB block · one thread · higher is better

MetricDigitalOcean c-4Vultr voc-c-4c-8gb-75s-amd
Read
7,433MiB/s19% of 40,000
36,657MiB/s92% of 40,000
Write
8,267MiB/s21% of 40,000
25,594MiB/s64% of 40,000

Bars share one scale across both rows. A memory copy workload is not part of this profile.

PerformanceReviewed data
DigitalOceanLondon, UK
VultrLondon, UK
03 /

Disk performance

fio · direct I/O · 1 MiB / QD32 sequential · 4 KiB / QD32 random

MetricDigitalOcean c-4Vultr voc-c-4c-8gb-75s-amd
Sequential read
8,795MB/s
4,197MB/s
Sequential write
1,685MB/s
2,133MB/s
Random read
130,395IOPS
117,225IOPS
Random write
108,809IOPS
99,265IOPS
Random read p95
354.3µs
354.3µs
Random write p95
469.0µs
452.6µs

Throughput and IOPS: higher is better. Latency: lower is better. Mixed 70/30 runs and p50/p99 latency are in each full report.

04 /

Network performance

LibreSpeed CLI · HTTPS / IPv4 · three streams · 10 seconds per direction

MetricDigitalOcean c-4Vultr voc-c-4c-8gb-75s-amd
Frankfurt · source
Network reportSeparate VM test · 17 Oct 2026, 18:12 UTCLondon, UK · Frankfurt, Germany (Clouvider)
Network reportSeparate VM test · 17 Oct 2026, 17:52 UTCLondon, UK · Frankfurt, Germany (Clouvider)
Frankfurt · Download
869.0Mbit/s
1,518Mbit/s
Frankfurt · Upload
914.6Mbit/s
1,013Mbit/s
Frankfurt · HTTP latency
16.0ms
12.2ms
Frankfurt · HTTP jitter
0.09ms
0.15ms
New York · source
Network reportSeparate VM test · 17 Oct 2026, 18:12 UTCLondon, UK · New York, United States (2) (Clouvider)
Network reportSeparate VM test · 17 Oct 2026, 17:52 UTCLondon, UK · New York, United States (2) (Clouvider)
New York · Download
909.5Mbit/s
1,182Mbit/s
New York · Upload
302.2Mbit/s
228.7Mbit/s
New York · HTTP latency
71.8ms
71.4ms
New York · HTTP jitter
0.20ms
0.06ms

Each network source is a linked same-VM supplement when available, otherwise a later test on a separate VM matching provider, plan, recorded region and resources. Frankfurt and New York are separate paths, with one trial per direction. HTTP latency and jitter are recorded; packet loss is not measured. Routes and times affect results; these trials do not establish maximum link capacity or long-term consistency.

PerformanceReviewed data
DigitalOcean4 vCPU · 7.8 GiB
Vultr4 vCPU · 7.7 GiB
05 /

PostgreSQL performance

PostgreSQL 16 · pgbench read/write · 4 clients · durability enabled

MetricDigitalOcean c-4Vultr voc-c-4c-8gb-75s-amd
In-memory throughput
4,224transactions/s
5,451transactions/s
In-memory average latency
0.95ms
0.73ms
Storage-bound throughput
3,518transactions/s
4,492transactions/s
Storage-bound average latency
1.14ms
0.89ms

Both dataset profiles shown. This profile records average latency, not percentiles; read throughput and latency together.

06 /

Consistency over 24 hours

Separate 24-hour profile · hourly CPU, memory read and random disk read

Hourly repeat runsCPU · memory · disk
DigitalOcean
Not measured24-hour run skipped
Vultr
Not measured24-hour run skipped
No hourly samples exist for these reports, so no chart is drawn.Skipped runs are not scores.

No 24-hour consistency or long-term reliability is established.

07 /

Inspect the source reports.

Different workloads reveal different trade-offs. Every number links back to its test.