cpx21 by Hetzner Cloud

cpx21 is a CPX 21 server offered by Hetzner Cloud with 3 vCPUs, 4 GiB of memory and 80 GB of storage. The pricing starts at 0.0578 USD per hour.
3 vCPU
4 GiB Memory
80 GB Storage
Spare SCore
7,981
(All-cores)
2,667
(Single-core)

Specifications

Server Metadata

Vendor ID
hcloud
Server ID
23
Name
cpx21
Description
CPX 21
Family
Regular Purpose
Hw Virt
Average Time To Start
15.67
Status
active
Observed At
2026-11-05T12:03:13.558568

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / ash
- 0.0578 USD/h
Hillsboro (US) / hil
- 0.0578 USD/h

Processor

vCPUs
3
Hypervisor
QEMU
CPU Allocation
Shared
CPU Cores
3
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU L1D Cache
32 KiB
CPU L1D Cache Total
96 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
96 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
2 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
16 MiB
CPU Flags
fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, ht, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, rep_good, nopl, cpuid, extd_apicid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, topoext, perfctr_core, ssbd, ibrs, ibpb, stibp, vmmcall, fsgsbase, bmi1, avx2, smep, bmi2, rdseed, adx, smap, clflushopt, clwb, sha_ni, xsaveopt, xsavec, xgetbv1, clzero, xsaveerptr, wbnoinvd, arat, umip, rdpid, arch_capabilities
Ecpus
3
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
4 GiB
Memory Amount Actual
4 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    80 GB
    Storage Type
    nvme ssd
    Storages
      NETWORK
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      20480 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A budget-friendly shared-core virtual machine combining strong single-threaded CPU performance with fast local NVMe SSD storage for lightweight workloads.

      Burstable & BudgetGeneral Purpose

      Hetzner Cloud cpx21 is an x86_64 virtual machine featuring 3 shared AMD EPYC vCPUs running at 2.0 GHz, 4.0 GB of RAM, and 80 GB of local NVMe SSD storage. Operating under a QEMU hypervisor, this instance delivers strong single-core CPU performance, as evidenced by a stress-ng single-core score of 2667.29. However, its multi-core capabilities and memory bandwidth are more limited, with memory benchmarks falling into the lower percentiles. The server lacks complimentary public IPv4 addresses. Qualitatively, the cpx21 represents a budget-friendly option with fast local storage, making it suitable for lightweight workloads, development environments, and single-threaded applications where memory throughput is not a primary constraint.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.25Score
      Precomputed compound score for Cache Intensive workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x_i / m_i)^(w_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 50% Redis RPS (pipeline=1, SET), 20% Redis RPS (pipeline=16, SET), 10% PassMark Memory Mark (composite), 10% Memory bandwidth (read, 16 MB ~ L3), 10% PassMark single-thread CPU. Rationale for component selection: In-memory key-value store workload, mixing direct Redis performance metrics with memory speed and latency benchmarks, and single-core CPU performance profiles.
      Component Score Weight Impact
      Raw Reference Normalized Target Actual
      Redis RPS (pipeline=1, SET) 312,887 ops/sec 1,937,246 ops/sec 0.16 50.00% 50.00% -60.00%
      Redis RPS (pipeline=16, SET) 2,643,743 ops/sec 11,803,344 ops/sec 0.22 20.00% 20.00% -26.00%
      PassMark Memory Mark (composite) 1,148 2,409 0.46 10.00% 10.00% -7.50%
      Memory bandwidth (read, 16 MB ~ L3) 43,615 MB/sec 108,490 MB/sec 0.4 10.00% 10.00% -8.80%
      PassMark single-thread CPU 2,341 Mops/s 2,365 Mops/s 0.96 10.00% 10.00% -0.41%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,469

      Geekbench Multi-Core

      Score: 3,733

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 6,521
      Compression
      		 64,262
      Encryption
      		 3,332
      Extended Instructions
      		 5,340
      Floating Point Maths
      		 12,276
      Integer Maths
      		 15,440
      Physics
      		 832
      Prime Numbers
      		 47
      Single Threaded
      		 2,341
      String Sorting
      		 9,032

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 1,148
      Database Operations
      		 2,502
      Memory Latency
      		 69
      Memory Read Cached
      		 23,055
      Memory Read Uncached
      		 14,938
      Memory Write
      		 15,531

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 362.63 327.17 0.90×
      bitops
      		 125,569 383,098 3.05×
      branch
      		 160,133 473,719 2.96×
      funccall
      		 515.54 1,532 2.97×
      funcret
      		 15,583 48,229 3.09×
      hash
      		 130,214 386,932 2.97×
      intmath
      		 55,223 162,234 2.94×
      nop
      		 269,690 799,078 2.96×
      prime
      		 368,013 1,077,776 2.93×
      rotate
      		 71,711 218,337 3.04×
      str
      		 770,638 2,120,548 2.75×
      wcs
      		 513,297 1,563,468 3.05×
      CryptographySingleMultiScaling
      crypt
      		 3,052 8,703 2.85×
      CompressionSingleMultiScaling
      jpeg
      		 697.52 2,147 3.08×
      zlib
      		 47.47 184.58 3.89×
      HypervisorSingleMultiScaling
      clock
      		 15,081 57,960 3.84×
      clone
      		 654.22 1,086 1.66×
      context
      		 4,868 14,436 2.97×
      cpu-sched
      		 66.26 190.6 2.88×
      eventfd
      		 21,273 310,553 14.60×
      fault
      		 10,175 29,525 2.90×
      fork
      		 4,241 15,820 3.73×
      getrandom
      		 50,712 150,776 2.97×
      hrtimers
      		 127,658 235,443 1.84×
      mprotect
      		 1,064,434 1,213,521 1.14×
      mtx
      		 23,810,311 302,439,457 12.70×
      munmap
      		 2,884 10,973 3.80×
      null
      		 847,882 2,462,251 2.90×
      pipe
      		 509,497 2,100,990 4.12×
      priv-instr
      		 680,970 1,795,757 2.64×
      resched
      		 1,185,020 603,553 0.51×
      switch
      		 31,755 750,505 23.63×
      timermix
      		 176,015 497,618 2.83×
      tlb-shootdown
      		 12,433 17,003 1.37×
      tsc
      		 653,073 1,934,484 2.96×
      usersyscall
      		 525,803 1,441,130 2.74×
      vdso
      		 67,749,877 201,163,122 2.97×
      vfork
      		 17,042 90,528 5.31×
      x86syscall
      		 9,480,199 28,910,378 3.05×
      yield
      		 2,701,871 2,527,566 0.94×
      zero
      		 4,280,239 12,291,507 2.87×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 13,441 39,936 2.97×
      expmath
      		 2,351 7,026 2.99×
      fma
      		 763,350 2,235,068 2.93×
      fp
      		 220.13 641.82 2.92×
      fractal
      		 6.6 19.6 2.97×
      hyperbolic
      		 3,094 9,270 3.00×
      logmath
      		 3,707 10,976 2.96×
      matrix
      		 2,648 7,794 2.94×
      matrix-3d
      		 754.43 2,027 2.69×
      monte-carlo
      		 279.86 818.24 2.92×
      mpfr
      		 1,335 3,768 2.82×
      powmath
      		 1,142 3,356 2.94×
      trig
      		 1,427 4,185 2.93×
      veccmp
      		 15,608 44,470 2.85×
      vecfp
      		 1,437 4,223 2.94×
      vecmath
      		 3,269 9,762 2.99×
      vecshuf
      		 507.6 1,502 2.96×
      vecwide
      		 23,027 67,783 2.94×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 7.8 23.4 3.00×
      bsearch
      		 243.35 746.26 3.07×
      bubblesort
      		 0.8 2.4 3.00×
      fibsearch
      		 304.04 880.99 2.90×
      heapsort
      		 8.4 25.6 3.05×
      hsearch
      		 6,934 21,453 3.09×
      insertionsort
      		 10.6 31.8 3.00×
      malloc
      		 2,439,989 6,385,763 2.62×
      mcontend
      		 118.32 445.57 3.77×
      mergesort
      		 27.8 79.8 2.87×
      qsort
      		 17.8 53 2.98×
      skiplist
      		 5,877 17,603 2.99×
      tree
      		 1.4 4 2.86×
      MemorySingleMultiScaling
      cache
      		 465,396 676,065 1.45×
      cachehammer
      		 261,602 753,424 2.88×
      cacheline
      		 36.35 94.8 2.61×
      l1cache
      		 161.87 433.1 2.68×
      memcpy
      		 334.15 1,023 3.06×
      memrate
      		 2.18 5.12 2.35×
      memthrash
      		 66.86 157.78 2.36×
      ptr-chase
      		 10,148,359 33,263,138 3.28×
      spinmem
      		 179.99 0.6 0.00×
      stream
      		 181.54 1,504 8.28×
      vm
      		 92,946 252,376 2.72×

      Stress-ng Raw Scores

      Stress-ng Relative Multicore Performance

      LLM Inference Speed for Prompt Processing

      LLM Inference Speed for Text Generation

      Static Web Server

      Redis

      PostgreSQL heavy read-only throughput

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYAccelerators
      cpx02 11.0 GiB0
      cpx12 12 GiB0
      cpx11 22 GiB0
      cpx22 24 GiB0
      cpx32 48 GiB0
      cpx31 48 GiB0
      cpx42 816 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      cpx21 FAQs