ecs.r7t.3xlarge by Alibaba Cloud

ecs.r7t.3xlarge is a ecs.r7t family (12 vCPUs, 96 GiB RAM, 0 GB storage) server offered by Alibaba Cloud with 12 vCPUs, 96 GiB of memory and 0 GB of storage. The pricing starts at 0.73 USD per hour.
12 vCPU
96 GiB Memory
Spare SCore
11,663
(All-cores)
1,893
(Single-core)

Specifications

Server Metadata

Vendor ID
alicloud
Name
ecs.r7t.3xlarge
Description
ecs.r7t family (12 vCPUs, 96 GiB RAM, 0 GB storage)
Family
ecs.r7t
Hw Virt
Status
active
Observed At
2026-10-31T01:12:05.396261

Availability

REGION / IDSPOTONDEMAND
Beijing (CN) / cn-beijing
- 0.73 USD/h
Hangzhou (CN) / cn-hangzhou
- 0.73 USD/h
Shanghai (CN) / cn-shanghai
- 0.73 USD/h
Seoul (KR) / ap-northeast-2
- 0.9071 USD/h

Processor

vCPUs
12
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
6
CPU Speed
2.7 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8369B
CPU L1D Cache
48 KiB
CPU L1D Cache Total
288 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
192 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
8 MiB
CPU L3 Cache
48 MiB
CPU L3 Cache Total
48 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, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, nonstop_tsc, cpuid, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, cpuid_fault, ibrs_enhanced, fsgsbase, tsc_adjust, sgx, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, wbnoinvd, arat, avx512vbmi, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, sgx_lc, fsrm, arch_capabilities
Ecpus
6.2
Scalability
51.67

System Resources and Accelerators

MEMORY
Memory Amount
96 GiB
Memory Amount Actual
48 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Network Speed Baseline
      8 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      An x86_64 memory-optimized instance featuring a high RAM-to-vCPU ratio for database operations and caching without local storage.

      Memory OptimizedGeneral Purpose

      Alibaba Cloud ecs.r7t.3xlarge is a memory-optimized instance featuring 12 dedicated vCPUs and 96.0 GB of RAM, powered by an Intel Xeon 8369B processor running at 2.7 GHz. Built on the x86_64 architecture under the KVM hypervisor, this instance provides an 8:1 RAM-to-vCPU ratio but lacks local storage and GPU accelerators. Performance benchmarks generally fall within the average range, with a single-core Geekbench score of 1599.0 and a multi-core score of 7867.0. It processes 11.97 million Redis SET operations per second and achieves a static web serving throughput of 16.92 GB/sec. However, a key tradeoff is its weak performance in medium 7B LLM prompt processing, which registers at 24.29 tokens/second. This instance is appropriate for memory-intensive applications, caching layers, and database operations that do not require local NVMe storage.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.83Score
      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) 1,567,825 ops/sec 1,918,343 ops/sec 0.84 50.00% 50.00% -8.30%
      Redis RPS (pipeline=16, SET) 8,376,325 ops/sec 11,704,734 ops/sec 0.7 20.00% 20.00% -6.90%
      PassMark Memory Mark (composite) 2,402 2,416 1 10.00% 10.00% 0.00%
      Memory bandwidth (read, 16 MB ~ L3) 83,087 MB/sec 108,466 MB/sec 0.75 10.00% 10.00% -2.80%
      PassMark single-thread CPU 2,372 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,599

      Geekbench Multi-Core

      Score: 7,867

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 16,516
      Compression
      		 189,148
      Encryption
      		 10,973
      Extended Instructions
      		 10,544
      Floating Point Maths
      		 25,861
      Integer Maths
      		 50,564
      Physics
      		 1,853
      Prime Numbers
      		 108
      Single Threaded
      		 2,372
      String Sorting
      		 26,440

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,402
      Database Operations
      		 5,826
      Memory Latency
      		 61
      Memory Read Cached
      		 23,485
      Memory Read Uncached
      		 11,201
      Memory Write
      		 10,692

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 290.27 291.28 1.00×
      bitops
      		 130,411 800,323 6.14×
      branch
      		 137,518 1,310,567 9.53×
      funccall
      		 636.64 3,906 6.14×
      funcret
      		 11,890 104,965 8.83×
      hash
      		 151,241 1,319,247 8.72×
      intmath
      		 61,398 454,509 7.40×
      nop
      		 190,142 1,001,071 5.26×
      prime
      		 394,704 2,560,893 6.49×
      rotate
      		 98,007 624,599 6.37×
      str
      		 868,592 5,721,077 6.59×
      wcs
      		 621,055 3,182,531 5.12×
      CryptographySingleMultiScaling
      crypt
      		 2,838 15,853 5.59×
      CompressionSingleMultiScaling
      jpeg
      		 728.8 5,624 7.72×
      zlib
      		 51.71 517.18 10.00×
      HypervisorSingleMultiScaling
      clock
      		 25,860 202,409 7.83×
      clone
      		 601.58 2,783 4.63×
      context
      		 4,843 43,679 9.02×
      cpu-sched
      		 61.03 754.71 12.37×
      eventfd
      		 103,139 1,044,097 10.12×
      fault
      		 18,494 129,578 7.01×
      fork
      		 5,943 45,976 7.74×
      getrandom
      		 51,173 355,402 6.95×
      hrtimers
      		 327,760 1,687,814 5.15×
      mprotect
      		 1,099,281 3,206,684 2.92×
      mtx
      		 14,577,689 416,453,582 28.57×
      munmap
      		 4,317 31,546 7.31×
      null
      		 801,270 5,898,672 7.36×
      pipe
      		 980,110 6,687,861 6.82×
      priv-instr
      		 831,395 6,270,474 7.54×
      resched
      		 5,384,879 1,767,368 0.33×
      switch
      		 216,405 2,111,097 9.76×
      timermix
      		 368,814 3,635,763 9.86×
      tlb-shootdown
      		 11,735 30,419 2.59×
      tsc
      		 769,783 6,838,663 8.88×
      usersyscall
      		 644,513 4,827,884 7.49×
      vdso
      		 112,366,220 765,554,535 6.81×
      vfork
      		 47,941 209,800 4.38×
      x86syscall
      		 9,093,138 74,755,975 8.22×
      yield
      		 9,595,056 9,499,486 0.99×
      zero
      		 4,638,567 33,672,816 7.26×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 14,837 115,220 7.77×
      expmath
      		 2,888 25,506 8.83×
      fma
      		 661,446 6,914,084 10.45×
      fp
      		 184.33 1,217 6.60×
      fractal
      		 5 44.4 8.88×
      hyperbolic
      		 3,076 27,410 8.91×
      logmath
      		 4,862 42,281 8.70×
      matrix
      		 3,504 32,397 9.25×
      matrix-3d
      		 799.96 3,003 3.75×
      monte-carlo
      		 258.79 2,091 8.08×
      mpfr
      		 1,412 9,076 6.43×
      powmath
      		 1,688 15,149 8.97×
      trig
      		 1,967 15,062 7.66×
      veccmp
      		 20,278 118,231 5.83×
      vecfp
      		 1,530 11,224 7.34×
      vecmath
      		 3,236 28,171 8.71×
      vecshuf
      		 666.13 4,357 6.54×
      vecwide
      		 31,768 221,975 6.99×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 8 48 6.00×
      bsearch
      		 249.56 2,008 8.04×
      bubblesort
      		 1 4.8 4.80×
      fibsearch
      		 288.96 2,197 7.60×
      heapsort
      		 9.4 65 6.91×
      hsearch
      		 7,362 48,886 6.64×
      insertionsort
      		 10.6 38.2 3.60×
      malloc
      		 2,621,506 21,582,354 8.23×
      mcontend
      		 142.03 2,450 17.25×
      mergesort
      		 26.8 225.79 8.42×
      qsort
      		 20.8 130 6.25×
      skiplist
      		 5,464 48,834 8.94×
      tree
      		 1.6 11.99 7.49×
      MemorySingleMultiScaling
      cache
      		 435,404 663,289 1.52×
      cachehammer
      		 366,177 3,784,828 10.34×
      cacheline
      		 61.55 695.14 11.29×
      l1cache
      		 901.72 2,279 2.53×
      memcpy
      		 407.82 2,408 5.90×
      memrate
      		 1.78 9.35 5.25×
      memthrash
      		 219.21 498.48 2.27×
      ptr-chase
      		 35,763,517 127,999,110 3.58×
      spinmem
      		 346.39 841.27 2.43×
      stream
      		 39.19 2,704 68.99×
      vm
      		 115,222 293,058 2.54×

      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

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYAccelerators
      ecs.r7t.large 216 GiB0
      ecs.r7t.xlarge 432 GiB0
      ecs.r7t.2xlarge 864 GiB0
      ecs.r7t.4xlarge 16128 GiB0
      ecs.r7t.6xlarge 24192 GiB0
      ecs.r7t.8xlarge 32256 GiB0
      ecs.r7t.16xlarge 64512 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      ecs.r7t.3xlarge FAQs