# Hetzner CPX31

[Ashburn, VA](https://rackcensus.com/locations/ashburn-vps-benchmarks "Every provider in Ashburn")

Benchmark complete

Finished Oct 22, 2026

Geekbench 7 single-core

1,266

Faster than 64% of 4 vCPU plans

Geekbench 7 multi-core

4,371

Faster than 70% of 4 vCPU plans

Disk 4K IOPS

48,920

fio random read and write, 50/50

Monthly price at test time

$73.49

59 multi-core points per dollar

Same price today

## Server

[Hetzner](https://rackcensus.com/vps-providers/hetzner-benchmarks)[CPX31](https://rackcensus.com/plans/u7t0te-hetzner-cpx31-benchmarks?location=ash)

-

Provider

Hetzner

-

Plan

CPX31

-

Location

Ashburn, VA

-

vCPU

4

-

RAM

8 GB

-

Storage

160 GB NVMe

-

Network

Unknown

-

OS image

ubuntu-24.04

-

Trigger

Scheduled

-

Queued at

Oct 21, 2026, 07:53:00 UTC

[Visit Hetzner](https://rackcensus.com/go/hetzner)

## CPU

| Version | Single-core | Multi-core | Result link |
| --- | --- | --- | --- |
| Geekbench 7 | 1,266 | 4,371 | [Geekbench Browser](https://browser.geekbench.com/v7/cpu/695300) |

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 | 1,32222nd of 64 | 4,0138th of 36 |
| Navigation | 1,24630th of 64 | Single-core only |
| HTML5 Browser | 1,20020th of 64 | Single-core only |
| PDF Viewer | 1,34220th of 64 | Single-core only |
| Photo Library | 1,21718th of 64 | 4,5157th of 36 |
| Clang | 1,01232nd of 64 | 4,0328th of 36 |
| Text Processing | 1,10823rd of 64 | 3,91810th of 36 |
| Asset Compression | 1,27617th of 64 | 5,1066th of 36 |
| HDR | 1,29616th of 64 | 3,89010th of 36 |
| Photo Editor | 1,52614th of 64 | 5,2916th of 36 |
| Ray Tracer | 1,19525th of 64 | 4,42910th of 36 |
| Structure from Motion | 1,56914th of 64 | Single-core only |
| Game Physics | 1,18325th of 64 | Single-core only |
| Video Encoder | 1,20718th of 64 | Single-core only |
| Audio Encoder | 1,31319th of 64 | Single-core only |
| Video Player | 1,36118th of 64 | Single-core only |

Rank among the 64 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.

## Disk

| Block size | Read | Write | Total |
| --- | --- | --- | --- |
| 4K | 95.4 MB/s (24,428 IOPS) | 95.7 MB/s (24,492 IOPS) | 191.1 MB/s (48,920 IOPS) |
| 64K | 881.6 MB/s (14,105 IOPS) | 886.2 MB/s (14,179 IOPS) | 1.73 GB/s (28,284 IOPS) |
| 512K | 1.32 GB/s (2,703 IOPS) | 1.39 GB/s (2,846 IOPS) | 2.71 GB/s (5,549 IOPS) |
| 1M | 1.53 GB/s (1,563 IOPS) | 1.63 GB/s (1,667 IOPS) | 3.15 GB/s (3,230 IOPS) |

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

## Network

### IPv4 transfer speed

Loading...

| Target | Protocol | Send | Receive |
| --- | --- | --- | --- |
| Leaseweb, NYC, NY, US (10G) | IPv4 | 8.63 Gbps | 8.91 Gbps |
| Eranium, Amsterdam, NL (100G) | IPv4 | 2.16 Gbps | 2.68 Gbps |
| Leaseweb, Singapore, SG (10G) | IPv4 | 705 Mbps | 965 Mbps |

Public iperf3 servers vary in capacity and availability. Compare a target only with itself over time.

## Application workloads

### PostgreSQL transactions
Measured

Durable transfers and indexed account lookups against a fixed relational dataset.

PostgreSQL transactions measurements| Repeat | Offered / s | transactions/s | p95 / p99 ms | Errors / dropped | Result |
| --- | --- | --- | --- | --- | --- |
| 1 | 100 | 100 | 5.89 / 6.69 | 0 / 0 | Met workload limits |
| 1 | 500 | 498.2 | 4.76 / 5.62 | 0 / 324 | Met workload limits |
| 1 | 1000 | 994.72 | 4.59 / 5.43 | 0 / 950 | Met workload limits |
| 1 | 3000 | 2991.04 | 4.32 / 5.24 | 0 / 1608 | Met workload limits |
| 2 | 100 | 100 | 5.76 / 6.46 | 0 / 0 | Met workload limits |
| 2 | 500 | 498.25 | 4.65 / 5.56 | 0 / 315 | Met workload limits |
| 2 | 1000 | 994.82 | 4.65 / 5.49 | 0 / 931 | Met workload limits |
| 2 | 3000 | 2990.84 | 4.32 / 5.3 | 0 / 1644 | Met workload limits |

p95 ≤ 50 ms · p99 ≤ 100 ms · errors ≤ 1.0%

### PostgreSQL large dataset
Failed

The same transaction mix against ten million accounts; the dataset never shrinks to fit a plan.

RuntimeError: RuntimeError: TimeoutError:

p95 ≤ 100 ms · p99 ≤ 250 ms · errors ≤ 1.0%

### Redis cache
Measured

A mixed cache workload with 1 KiB values, expiration, misses and eviction.

Redis cache measurements| Repeat | Offered / s | operations/s | p95 / p99 ms | Errors / dropped | Result |
| --- | --- | --- | --- | --- | --- |
| 1 | 1000 | 1000 | 1.6 / 1.79 | 0 / 0 | Met workload limits |
| 1 | 5000 | 4999.97 | 1.55 / 1.73 | 0 / 0 | Met workload limits |
| 1 | 10000 | 9999.94 | 1.5 / 1.65 | 0 / 0 | Met workload limits |
| 1 | 25000 | 24861.2 | 5 / 12.56 | 0 / 24966 | load generator saturated |
| 2 | 1000 | 1000 | 1.6 / 1.79 | 0 / 0 | Met workload limits |
| 2 | 5000 | 4999.97 | 1.57 / 1.76 | 0 / 0 | Met workload limits |
| 2 | 10000 | 9999.94 | 1.5 / 1.65 | 0 / 0 | Met workload limits |
| 2 | 25000 | 24938.64 | 3.49 / 10.68 | 0 / 11030 | load generator saturated |

p95 ≤ 10 ms · p99 ≤ 25 ms · errors ≤ 1.0%

### Redis persistent queue
Measured

Enqueue, consume and acknowledge payloads with append-only persistence.

Redis persistent queue measurements| Repeat | Offered / s | jobs/s | p95 / p99 ms | Errors / dropped | Result |
| --- | --- | --- | --- | --- | --- |
| 1 | 100 | 100 | 3.87 / 4.27 | 0 / 0 | Met workload limits |
| 1 | 500 | 500 | 2.83 / 3.19 | 0 / 0 | Met workload limits |
| 1 | 1000 | 1000 | 2.87 / 3.19 | 0 / 0 | Met workload limits |
| 1 | 3000 | 2999.99 | 2.2 / 2.87 | 0 / 0 | Met workload limits |
| 2 | 100 | 100 | 3.87 / 4.27 | 0 / 0 | Met workload limits |
| 2 | 500 | 500 | 2.87 / 3.23 | 0 / 0 | Met workload limits |
| 2 | 1000 | 1000 | 2.83 / 3.19 | 0 / 0 | Met workload limits |
| 2 | 3000 | 2999.99 | 2.27 / 2.95 | 0 / 0 | Met workload limits |

p95 ≤ 20 ms · p99 ≤ 50 ms · errors ≤ 1.0%

### Discourse community
Measured

Signed-in reading, search, posting and replies in a populated Rails forum.

Discourse community measurements| Repeat | Offered / s | journeys/s | p95 / p99 ms | Errors / dropped | Result |
| --- | --- | --- | --- | --- | --- |
| 1 | 2 | 1.96 | 232.41 / 313.6 | 8 / 0 | error limit exceeded |
| 1 | 5 | 4.69 | 192.2 / 298.33 | 56 / 0 | error limit exceeded |
| 1 | 10 | 9.19 | 184.66 / 283.8 | 146 / 0 | error limit exceeded |
| 1 | 25 | 22.68 | 194.13 / 237.1 | 416 / 0 | error limit exceeded |
| 2 | 2 | 1.96 | 227.81 / 323.13 | 8 / 0 | error limit exceeded |
| 2 | 5 | 4.69 | 190.29 / 301.32 | 56 / 0 | error limit exceeded |
| 2 | 10 | 9.19 | 188.39 / 286.65 | 146 / 0 | error limit exceeded |
| 2 | 25 | 22.68 | 196.08 / 244.31 | 416 / 0 | error limit exceeded |

p95 ≤ 1500 ms · p99 ≤ 3000 ms · errors ≤ 1.0%

### n8n workflows
Measured

Webhook, transformation, branching and a verified final response.

n8n workflows measurements| Repeat | Offered / s | workflows/s | p95 / p99 ms | Errors / dropped | Result |
| --- | --- | --- | --- | --- | --- |
| 1 | 5 | 5 | 25.67 / 29.66 | 0 / 0 | Met workload limits |
| 1 | 20 | 20 | 22.2 / 27.03 | 0 / 0 | Met workload limits |
| 1 | 50 | 50 | 18.59 / 23.63 | 0 / 0 | Met workload limits |
| 1 | 100 | 85.74 | 3227.16 / 3460.03 | 0 / 2381 | latency limit exceeded |
| 2 | 5 | 5 | 25.67 / 28.17 | 0 / 0 | Met workload limits |
| 2 | 20 | 20 | 21.97 / 26.21 | 0 / 0 | Met workload limits |
| 2 | 50 | 50 | 18.4 / 22.91 | 0 / 0 | Met workload limits |
| 2 | 100 | 86.38 | 3195.2 / 3292.05 | 0 / 2279 | latency limit exceeded |

p95 ≤ 1000 ms · p99 ≤ 2000 ms · errors ≤ 1.0%

### n8n queue workers
Measured

Completed queued workflows including waiting time and worker execution.

n8n queue workers measurements| Repeat | Offered / s | workflows/s | p95 / p99 ms | Errors / dropped | Result |
| --- | --- | --- | --- | --- | --- |
| 1 | 5 | 5 | 32.2 / 39.91 | 0 / 0 | Met workload limits |
| 1 | 20 | 20 | 29.36 / 36.04 | 0 / 0 | Met workload limits |
| 1 | 50 | 50 | 26.75 / 37.54 | 0 / 0 | Met workload limits |
| 1 | 100 | 99.99 | 143.77 / 254.27 | 0 / 0 | Met workload limits |
| 2 | 5 | 5 | 33.2 / 40.74 | 0 / 0 | Met workload limits |
| 2 | 20 | 20 | 28.46 / 33.89 | 0 / 0 | Met workload limits |
| 2 | 50 | 50 | 26.75 / 38.71 | 0 / 0 | Met workload limits |
| 2 | 100 | 99.99 | 343.07 / 435.88 | 0 / 0 | Met workload limits |

p95 ≤ 2000 ms · p99 ≤ 4000 ms · errors ≤ 1.0%

### Ghost publishing
Measured

Readers, authenticated draft creation, publishing and image uploads.

Ghost publishing measurements| Repeat | Offered / s | journeys/s | p95 / p99 ms | Errors / dropped | Result |
| --- | --- | --- | --- | --- | --- |
| 1 | 5 | 5 | 329.64 / 364.24 | 0 / 0 | Met workload limits |
| 1 | 20 | 20 | 367.89 / 398.45 | 0 / 0 | Met workload limits |
| 1 | 50 | 43.88 | 7013.92 / 7013.92 | 879 / 12 | latency limit exceeded |
| 1 | 100 | 49.4 | 7013.92 / 7013.92 | 908 / 7957 | latency limit exceeded |
| 2 | 5 | 5 | 319.92 / 336.29 | 0 / 0 | Met workload limits |
| 2 | 20 | 20 | 346.51 / 390.58 | 0 / 0 | Met workload limits |
| 2 | 50 | 43.9 | 7013.92 / 7013.92 | 881 / 0 | latency limit exceeded |
| 2 | 100 | 50.78 | 7013.92 / 7013.92 | 951 / 7666 | latency limit exceeded |

p95 ≤ 1000 ms · p99 ≤ 2000 ms · errors ≤ 1.0%

### Formbricks / Next.js
Failed

Public survey rendering, persisted responses and authenticated analysis.

RuntimeError: RuntimeError: TimeoutError:

p95 ≤ 1000 ms · p99 ≤ 2000 ms · errors ≤ 1.0%

### Elasticsearch search and ingestion
Measured

Full-text search, filtering and aggregations while new documents are indexed.

Elasticsearch search and ingestion measurements| Repeat | Offered / s | operations/s | p95 / p99 ms | Errors / dropped | Result |
| --- | --- | --- | --- | --- | --- |
| 1 | 10 | 10 | 9.89 / 12.56 | 0 / 0 | Met workload limits |
| 1 | 50 | 50 | 8.2 / 10.56 | 0 / 0 | Met workload limits |
| 1 | 100 | 100 | 7.16 / 9.68 | 0 / 0 | Met workload limits |
| 1 | 250 | 250 | 6.54 / 8.96 | 0 / 0 | Met workload limits |
| 2 | 10 | 10 | 10.8 / 13.68 | 0 / 0 | Met workload limits |
| 2 | 50 | 50 | 8.02 / 10.45 | 0 / 0 | Met workload limits |
| 2 | 100 | 100 | 7.24 / 9.78 | 0 / 0 | Met workload limits |
| 2 | 250 | 250 | 6.61 / 9.16 | 0 / 0 | Met workload limits |

p95 ≤ 250 ms · p99 ≤ 500 ms · errors ≤ 1.0%

### GitHub self-hosted runner
Failed

A pinned build and test workflow with separate cold and warm dependency caches.

ValueError: set RUNNER\_BENCHMARK\_REPOSITORY and RUNNER\_BENCHMARK\_REVISION to the repository and commit hosting benchmark-runner.yml

p95 ≤ 3600000 ms · p99 ≤ 3600000 ms · errors ≤ 1.0%

### Odoo Community sales
Failed

Customer lookup, sales order confirmation, stock operations and reporting.

RuntimeError: fixture command in rc-odoo failed: -packages/odoo/cli/shell.py", line 148, in shell self.console(local\_vars) File "/usr/lib/python3/dist-packages/odoo/cli/shell.py", line 82, in console exec(sys.stdin.read(), local\_vars) File "\<string\>", line 1, in \<module\> PermissionError: [Errno 13] Permission denied: '/tmp/rc-seed.py'

p95 ≤ 2000 ms · p99 ≤ 4000 ms · errors ≤ 1.0%

## Advertised vs. measured

| Spec | Advertised | Measured |
| --- | --- | --- |
| vCPU | 4 | 4 |
| CPU | Shared vCPU | 0% of busy CPU time stolen |
| RAM | 8 GB | 7.6 GiB |
| Storage | 160 GB NVMe | 150.1 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:** AMD EPYC-Rome Processor

**CPU cores:** 4

**CPU frequency:** 2445 MHz

**AES-NI:** Yes

**VM-x/AMD-V:** No

**RAM reported:** 7.6 GiB

**Swap reported:** 0 MiB

**Disk reported:** 150.1 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:** Yes

## Advertised at test time

**Plan:** CPX31

**Product line:** regular\_purpose

**Location:** Ashburn, VA

**vCPU:** 4 shared vCPU

**Architecture:** x86\_64

**RAM:** 8 GB

**Storage:** 160 GB NVMe

**Virtualization:** KVM

**Network:** Unknown

**Transfer:** 3.3 TB

**Port 25:** On request

**Monthly price at test time:** $73.49

**Hourly price at test time:** $0.12

**YABS version:** v2026-09-20

**Ran at:** Oct 22, 2026, 18:11:37 UTC

**Parser version:** 5

## Run timeline

**Queued:** Oct 21, 2026, 07:53:00 UTC

**First update from the server:** Oct 22, 2026, 18:11:31 UTC

**Completed:** Oct 22, 2026, 22:46:30 UTC

**Server deleted:** Oct 22, 2026, 22:46:30 UTC

**Cost of this run:** $0.54

Tests 47 of 51 done Live output 1359 lines

Setup 4 cores, 7.6 GiB RAM 4 of 4Done

Disk (fio) 200 MB/s at 4k, 3.38 GB/s at 1m 5 of 5Done

Network, IPv4 (iperf3) Median 2.16 Gbit/s send, 2.68 Gbit/s receive 3 of 3Done

Geekbench 7, single-core Score 1,266 17 of 17Done

Geekbench 7, multi-core Score 4,371 9 of 9Done

Web apps 4 failed 8 of 12Some failed

TestResultTime

PostgreSQL transactions 8 measured trials completed 8 trials Measurements, 8 measured trials completed 29m 21s

PostgreSQL large dataset RuntimeError: RuntimeError: TimeoutError: Stopped RuntimeError: RuntimeError: TimeoutError: 1m 26s

Redis cache 8 measured trials completed 8 trials Measurements, 8 measured trials completed 28m 27s

Redis persistent queue 8 measured trials completed 8 trials Measurements, 8 measured trials completed 28m 22s

Discourse community 8 measured trials completed 8 trials Measurements, 8 measured trials completed 35m 06s

n8n workflows 8 measured trials completed 8 trials Measurements, 8 measured trials completed 30m 44s

n8n queue workers 8 measured trials completed 8 trials Measurements, 8 measured trials completed 30m 30s

Ghost publishing 8 measured trials completed 8 trials Measurements, 8 measured trials completed 32m 37s

Formbricks / Next.js RuntimeError: RuntimeError: TimeoutError: Stopped RuntimeError: RuntimeError: TimeoutError: 13m 11s

Elasticsearch search and ingestion 8 measured trials completed 8 trials Measurements, 8 measured trials completed 33m 27s

GitHub self-hosted runner ValueError: set RUNNER\_BENCHMARK\_REPOSITORY and RUNNER\_BENCHMARK\_REVISION to the repository and commit hosting benchmark-runner.yml Stopped ValueError: set RUNNER\_BENCHMARK\_REPOSITORY and RUNNER\_BENCHMARK\_REVISION to the repository and commit hosting benchmark-runner.yml 0s

Odoo Community sales Application workloads Stopped RuntimeError: fixture command in rc-odoo failed: -packages/odoo/cli/shell.py", line 148, in shell self.console(local\_vars) File "/usr/lib/python3/dist-packages/odoo/cli/shell.py", line 82, in console exec(sys.stdin.read(), local\_vars) File "\<string\>", line 1, in \<module\> PermissionError: [Errno 13] Permission denied: '/tmp/rc-seed.py' 1m 30s

Finish Results saved 1 of 1Done

Watch party 0 watching

This party closed at 23:46 UTC. It's read only now.

## Watch party

Loading the party