netcup VPS 1000 G12 benchmarked: how fast is it really?

Description and use

Detailed performance benchmark of netcup VPS 1000 G12 covering CPU, memory, NVMe, and network. Results show strong performance and provide commands for users to replicate the tests.

Problem

Users need to know the real performance of a netcup VPS 1000 G12 to decide if it meets their self‑hosting needs.

Outcome

The VPS delivers strong CPU (≈1,500 events/s per core, near‑linear scaling), high memory throughput (~30 GB/s), excellent NVMe performance (101k read IOPS, 67k write IOPS, 4.3 GB/s read, 3.1 GB/s write), and fast network (~246 MB/s download, ~12 ms latency).

Workflow

• Install benchmark tools: sudo apt update && sudo apt install -y sysbench fio p7zip-full
• Check server specs: grep -m1 "model name" /proc/cpuinfo && nproc && free -h
• Verify steal time: vmstat 1 3
• Run CPU single‑core test: sysbench cpu --cpu-max-prime=20000 --threads=1 run
• Run CPU multi‑core test: sysbench cpu --cpu-max-prime=20000 --threads=4 run
• Run 7‑Zip benchmark: 7z b
• Run AES‑256‑GCM test: openssl speed -evp aes-256-gcm
• Run memory throughput test: sysbench memory --memory-block-size=1M --memory-total-size=30G --threads=4 run
• Run NVMe random read test: fio --name=rr --ioengine=libaio --direct=1 --rw=randread --bs=4k --numjobs=4 --iodepth=32 --size=512M --runtime=20 --time_based --group_reporting
• Run NVMe random write test: fio --name=rw --ioengine=libaio --direct=1 --rw=randwrite --bs=4k --numjobs=4 --iodepth=32 --size=512M --runtime=20 --time_based --group_reporting
• Run NVMe sequential read test: fio --name=sr --ioengine=libaio --direct=1 --rw=read --bs=1M --numjobs=1 --iodepth=16 --size=2G --runtime=15 --time_based
• Run NVMe sequential write test: fio --name=sw --ioengine=libaio --direct=1 --rw=write --bs=1M --numjobs=1 --iodepth=16 --size=2G --runtime=15 --time_based

Evidence

CPU – 1 core (sysbench) 1,495 events/s

Source

NVMe – 4K random read 101,000 IOPS

Source

Download (Falkenstein) ~246 MB/s

Source