ecs.gn6i-c8g1.2xlarge by Alibaba Cloud

ecs.gn6i-c8g1.2xlarge is a ecs.gn6i family (8 vCPUs, 31 GiB RAM, 0 GB storage, 1xT4 16384.0 GiB VRAM) server offered by Alibaba Cloud with 8 vCPUs, 31 GiB of memory and 0 GB of storage. The pricing starts at 0.3583 USD per hour.
8 vCPU
31 GiB Memory
1 GPU
Spare SCore
5,913
(All-cores)
1,110
(Single-core)

Specifications

Server Metadata

Vendor ID
alicloud
Name
ecs.gn6i-c8g1.2xlarge
Description
ecs.gn6i family (8 vCPUs, 31 GiB RAM, 0 GB storage, 1xT4 16384.0 GiB VRAM)
Family
ecs.gn6i
Hw Virt
Status
active
Observed At
2026-10-24T15:16:59.070354

Availability

REGION / IDSPOTONDEMAND
Virginia (US) / us-east-1
0.4561 USD/h 1.303 USD/h
Hong Kong (HK) / cn-hongkong
- 1.343 USD/h
Jakarta (ID) / ap-southeast-5
- 1.414 USD/h
Tokyo (JP) / ap-northeast-1
0.42995 USD/h 1.433 USD/h
Kuala Lumpur (MY) / ap-southeast-3
0.5194 USD/h 1.484 USD/h
Singapore (SG) / ap-southeast-1
- 1.515 USD/h
Chengdu (CN) / cn-chengdu
0.6826 USD/h 1.9503 USD/h
Qingdao (CN) / cn-qingdao
0.7584 USD/h 2.167 USD/h
Beijing (CN) / cn-beijing
- 2.167 USD/h
Guangzhou (CN) / cn-guangzhou
- 2.167 USD/h
Hangzhou (CN) / cn-hangzhou
- 2.167 USD/h
Heyuan (CN) / cn-heyuan
- 2.167 USD/h
Shanghai (CN) / cn-shanghai
- 2.167 USD/h
Shenzhen (CN) / cn-shenzhen
- 2.167 USD/h

Processor

vCPUs
8
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
4
CPU Speed
2.5 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8163
CPU L1D Cache
32 KiB
CPU L1D Cache Total
128 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
128 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
4 MiB
CPU L3 Cache
33 MiB
CPU L3 Cache Total
33 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, pti, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, arat
Ecpus
5.3
Scalability
66.25

System Resources and Accelerators

MEMORY
Memory Amount
31 GiB
Memory Amount Actual
31 GiB
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
16 GiB
Accelerator Memory Total
16 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Turing
Accelerator Model
T4
Accelerators
  • NVIDIA Turing Tesla T4 (Memory amount: 15360, Firmware version: 590.48.01, BIOS version: 90.04.96.00.9F, Clock rate: 1590)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Network Speed Baseline
    5 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    An entry-level GPU instance combining dedicated Intel Xeon processors with an NVIDIA T4 accelerator for efficient machine learning inference.

    GPU AcceleratedGeneral Purpose

    Alibaba Cloud ecs.gn6i-c8g1.2xlarge is a GPU-accelerated instance featuring 8 dedicated Intel Xeon 8163 vCPUs running at 2.5 GHz, 31.0 GB of system memory, and a single NVIDIA T4 GPU with 16 GB of VRAM. It does not include local storage and provides a baseline network bandwidth of 5 Gbps. While CPU-bound benchmarks, such as stress-ng and Redis operations, rank in the bottom 25 percent, the instance excels in GPU-driven workloads. Specifically, it achieves top-tier performance in LLM inference prompt processing, delivering 1,134.43 tokens per second on a 7B model. This hardware profile offers a cost-effective entry point for machine learning inference and small-scale AI workloads, though it presents a clear tradeoff in general-purpose CPU performance.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.4Score
    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) 655,186 ops/sec 1,919,289 ops/sec 0.35 50.00% 50.00% -41.00%
    Redis RPS (pipeline=16, SET) 3,806,136 ops/sec 11,728,058 ops/sec 0.32 20.00% 20.00% -20.00%
    PassMark Memory Mark (composite) 1,668 2,416 0.71 10.00% 10.00% -3.40%
    Memory bandwidth (read, 16 MB ~ L3) 41,882 MB/sec 108,466 MB/sec 0.38 10.00% 10.00% -9.20%
    PassMark single-thread CPU 1,670 Mops/s 2,365 Mops/s 0.71 10.00% 10.00% -3.40%

    GPU Bandwidth and Latency

    Node (all GPUs)
    Node baseline directional bandwidth
    		10.6 GB/s
    Node GPU-to-host bandwidth
    		11.8 GB/s
    Node host-to-GPU bandwidth
    		11.1 GB/s
    Single GPU slot
    Per-GPU GPU-to-host bandwidth
    		12.2 GB/s
    Per-GPU host-to-GPU bandwidth
    		11.9 GB/s
    Per-GPU host-device latency
    		987 ns
    Benchmark Environment
    Driver Version
    		 590.48.01
    CUDA Runtime Version
    		 13.1
    nvbandwidth Version
    		 v0.8
    GPU Count
    		 1
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		0.75

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 935

    Geekbench Multi-Core

    Score: 3,617

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 7,041
    Compression
    		 91,387
    Encryption
    		 2,737
    Extended Instructions
    		 5,917
    Floating Point Maths
    		 10,615
    Integer Maths
    		 19,774
    Physics
    		 808
    Prime Numbers
    		 49
    Single Threaded
    		 1,670
    String Sorting
    		 12,186

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 1,668
    Database Operations
    		 2,207
    Memory Latency
    		 78
    Memory Read Cached
    		 19,519
    Memory Read Uncached
    		 6,842
    Memory Write
    		 7,331

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 177.41 174.38 0.98×
    bitops
    		 100,055 398,527 3.98×
    branch
    		 122,183 652,869 5.34×
    funccall
    		 450.5 1,890 4.20×
    funcret
    		 9,009 53,135 5.90×
    hash
    		 104,034 613,573 5.90×
    intmath
    		 17,759 109,007 6.14×
    nop
    		 152,042 526,479 3.46×
    prime
    		 261,142 1,169,279 4.48×
    rotate
    		 76,812 390,066 5.08×
    str
    		 636,499 3,250,426 5.11×
    wcs
    		 423,145 1,850,406 4.37×
    CryptographySingleMultiScaling
    crypt
    		 1,936 7,563 3.91×
    CompressionSingleMultiScaling
    jpeg
    		 494.57 2,468 4.99×
    zlib
    		 39.67 256.19 6.46×
    HypervisorSingleMultiScaling
    clock
    		 15,379 84,972 5.53×
    clone
    		 366.4 1,363 3.72×
    context
    		 1,590 8,571 5.39×
    cpu-sched
    		 64.55 515.2 7.98×
    eventfd
    		 72,999 377,945 5.18×
    fault
    		 10,919 58,696 5.38×
    fork
    		 3,472 19,372 5.58×
    getrandom
    		 35,847 177,833 4.96×
    hrtimers
    		 496,566 742,321 1.49×
    mprotect
    		 726,400 1,004,451 1.38×
    mtx
    		 10,964,376 175,584,442 16.01×
    munmap
    		 2,462 12,903 5.24×
    null
    		 170,137 856,877 5.04×
    pipe
    		 784,254 1,994,863 2.54×
    priv-instr
    		 354,344 1,866,728 5.27×
    resched
    		 1,441,740 622,766 0.43×
    switch
    		 170,564 841,608 4.93×
    timermix
    		 344,634 1,920,483 5.57×
    tlb-shootdown
    		 9,579 18,852 1.97×
    tsc
    		 791,777 4,448,910 5.62×
    usersyscall
    		 249,704 1,306,533 5.23×
    vdso
    		 64,413,245 455,036,473 7.06×
    vfork
    		 27,107 104,652 3.86×
    x86syscall
    		 1,916,551 9,781,133 5.10×
    yield
    		 3,369,652 3,785,250 1.12×
    zero
    		 1,264,340 6,091,029 4.82×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 12,946 66,883 5.17×
    expmath
    		 2,132 13,039 6.12×
    fma
    		 480,466 3,337,626 6.95×
    fp
    		 132 780.9 5.92×
    fractal
    		 4.2 24.6 5.86×
    hyperbolic
    		 2,218 13,979 6.30×
    logmath
    		 3,634 21,890 6.02×
    matrix
    		 2,407 15,436 6.41×
    matrix-3d
    		 561.42 1,511 2.69×
    monte-carlo
    		 85.86 504.6 5.88×
    mpfr
    		 971.76 4,206 4.33×
    powmath
    		 1,261 7,732 6.13×
    trig
    		 1,365 7,389 5.41×
    veccmp
    		 12,191 48,787 4.00×
    vecfp
    		 1,766 8,770 4.97×
    vecmath
    		 1,664 10,640 6.39×
    vecshuf
    		 746.56 3,223 4.32×
    vecwide
    		 45,057 212,640 4.72×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 5.8 23.8 4.10×
    bsearch
    		 196.71 821.71 4.18×
    bubblesort
    		 0.6 1.6 2.67×
    fibsearch
    		 223.38 1,118 5.01×
    heapsort
    		 6.8 32.4 4.76×
    hsearch
    		 3,985 20,106 5.05×
    insertionsort
    		 6.4 25.6 4.00×
    malloc
    		 1,701,314 13,213,400 7.77×
    mcontend
    		 145.14 1,871 12.89×
    mergesort
    		 21.2 111.8 5.27×
    qsort
    		 15 74.4 4.96×
    skiplist
    		 4,166 23,567 5.66×
    tree
    		 1.2 4.8 4.00×
    MemorySingleMultiScaling
    cache
    		 255,576 456,626 1.79×
    cachehammer
    		 248,706 1,808,652 7.27×
    cacheline
    		 33.75 244.54 7.25×
    l1cache
    		 180.7 777.89 4.30×
    memcpy
    		 303.69 1,227 4.04×
    memrate
    		 0.97 4.57 4.71×
    memthrash
    		 114.16 253.17 2.22×
    ptr-chase
    		 28,771,586 69,595,631 2.42×
    spinmem
    		 317.79 457.71 1.44×
    stream
    		 35.91 1,329 37.02×
    vm
    		 30,207 266,741 8.83×

    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.gn6i-c4g1.xlarge 415 GiB1
    ecs.gn6i-c16g1.4xlarge 1662 GiB1
    ecs.gn6i-c24g1.6xlarge 2493 GiB1
    ecs.gn6i-c40g1.10xlarge 40155 GiB1
    ecs.gn6i-c24g1.12xlarge 48186 GiB2
    ecs.gn6i-c24g1.24xlarge 96372 GiB4

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    ecs.gn6i-c8g1.2xlarge FAQs