G3 by Microsoft Azure

G3 is a G family [Intel processor] 8 vCPUs server offered by Microsoft Azure with 8 vCPUs, 112 GiB of memory and 1.57 TB of storage. The pricing starts at 0.3578 USD per hour.
8 vCPU
112 GiB Memory
1.57 TB Storage
Spare SCore
5,489
(All-cores)
870
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_G3
Name
G3
API Reference
Standard_G3
Description
G family [Intel processor] 8 vCPUs
Family
G
Hw Virt
Average Time To Start
19
Status
planned-for-retirement
Observed At
2026-11-01T17:16:08.874053

Availability

REGION / IDSPOTONDEMAND
Canada East (CA) / canadaeast
0.3578 USD/h -
East US 2 (US) / eastus2
0.7559 USD/h -
UK South (GB) / uksouth
- 1.757 USD/h
Canada Central (CA) / canadacentral
0.5336 USD/h 1.936 USD/h
West US 2 (US) / westus2
0.3624 USD/h 1.961 USD/h
Japan East (JP) / japaneast
- 2.302 USD/h
West US (US) / westus
0.4509 USD/h 2.44 USD/h
Australia East (AU) / australiaeast
0.4719 USD/h 2.552 USD/h
Southeast Asia (SG) / southeastasia
0.4879 USD/h 2.64 USD/h
West Europe (NL) / westeurope
0.5174 USD/h 2.8 USD/h

Processor

vCPUs
8
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
8
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
E5-2698B v3
CPU L1D Cache
48 KiB
CPU L1D Cache Total
384 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
256 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
10 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, cpuid, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, pti, fsgsbase, bmi1, avx2, smep, bmi2, erms, invpcid, xsaveopt, md_clear
Ecpus
6.3
Scalability
78.75

System Resources and Accelerators

MEMORY
Memory Amount
112 GiB
Memory Amount Actual
112 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    1573 GB
    Storage Type
    ssd
    Storages
    • 1573 GB ssd (temp disk)
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    A memory-optimized server combining high RAM capacity and substantial local storage for database and caching workloads with moderate compute requirements.

    Memory OptimizedStorage & Database

    Microsoft Azure G3 is an x86_64 memory-optimized server instance powered by an Intel Xeon E5-2698B v3 processor with 8 dedicated physical cores and 8 vCPUs running at 2.0 GHz. It features 112.0 GB of RAM (14.0 GB per core) and 1573 GB of local storage, managed via the Microsoft Hyper-V hypervisor. Benchmark results show average performance in multi-core Geekbench tests, software compilation, and Redis SET operations (9.45 million operations per second), though single-core CPU performance and uncached memory write speeds are weak to poor. Qualitatively, the G3 offers high memory and storage density relative to its compute resources, presenting a tradeoff between large capacity and older processor performance. It is best suited for memory-intensive workloads, database operations, caching layers, and static web serving that do not require high single-core computational throughput.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.47Score
    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) 763,401 ops/sec 1,918,343 ops/sec 0.4 50.00% 50.00% -37.00%
    Redis RPS (pipeline=16, SET) 5,488,225 ops/sec 11,704,734 ops/sec 0.46 20.00% 20.00% -14.00%
    PassMark Memory Mark (composite) 2,072 2,416 0.88 10.00% 10.00% -1.30%
    Memory bandwidth (read, 16 MB ~ L3) 36,398 MB/sec 108,466 MB/sec 0.33 10.00% 10.00% -10.00%
    PassMark single-thread CPU 1,897 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,057

    Geekbench Multi-Core

    Score: 4,846

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 8,575
    Compression
    		 121,516
    Encryption
    		 2,263
    Extended Instructions
    		 7,549
    Floating Point Maths
    		 18,264
    Integer Maths
    		 24,557
    Physics
    		 1,078
    Prime Numbers
    		 93
    Single Threaded
    		 1,897
    String Sorting
    		 17,340

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,072
    Database Operations
    		 4,425
    Memory Latency
    		 65
    Memory Read Cached
    		 21,240
    Memory Read Uncached
    		 9,030
    Memory Write
    		 7,903

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 186.07 185.13 0.99×
    bitops
    		 93,623 745,538 7.96×
    branch
    		 98,290 784,285 7.98×
    funccall
    		 455.35 3,627 7.97×
    funcret
    		 8,600 67,244 7.82×
    hash
    		 108,823 862,677 7.93×
    intmath
    		 43,687 348,130 7.97×
    nop
    		 134,260 1,070,063 7.97×
    prime
    		 287,875 2,292,951 7.97×
    rotate
    		 69,986 557,967 7.97×
    str
    		 644,347 5,133,685 7.97×
    wcs
    		 448,804 3,397,739 7.57×
    CryptographySingleMultiScaling
    crypt
    		 2,035 16,217 7.97×
    CompressionSingleMultiScaling
    jpeg
    		 495.31 3,929 7.93×
    zlib
    		 29.14 286.99 9.85×
    HypervisorSingleMultiScaling
    clock
    		 17,929 120,116 6.70×
    clone
    		 1,256 5,989 4.77×
    context
    		 1,507 11,924 7.91×
    cpu-sched
    		 69.81 526.88 7.55×
    eventfd
    		 34,333 642,162 18.70×
    fault
    		 9,906 61,593 6.22×
    fork
    		 4,126 22,473 5.45×
    getrandom
    		 34,424 274,111 7.96×
    hrtimers
    		 562,006 824,497 1.47×
    mprotect
    		 1,058,619 1,573,113 1.49×
    mtx
    		 12,236,151 231,339,767 18.91×
    munmap
    		 2,919 18,698 6.41×
    null
    		 163,637 1,295,087 7.91×
    pipe
    		 848,302 3,766,611 4.44×
    priv-instr
    		 346,403 2,702,189 7.80×
    resched
    		 2,029,240 902,138 0.44×
    switch
    		 107,678 1,747,525 16.23×
    timermix
    		 166,641 1,283,089 7.70×
    tlb-shootdown
    		 5,474 20,892 3.82×
    tsc
    		 641,513 5,104,037 7.96×
    usersyscall
    		 243,366 1,911,707 7.86×
    vdso
    		 65,286,091 517,998,479 7.93×
    vfork
    		 25,220 153,783 6.10×
    x86syscall
    		 1,824,031 14,492,288 7.95×
    yield
    		 4,701,777 4,983,228 1.06×
    zero
    		 1,371,332 10,930,205 7.97×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 10,607 84,452 7.96×
    expmath
    		 2,070 16,492 7.97×
    fma
    		 486,225 3,875,639 7.97×
    fp
    		 132 1,048 7.94×
    fractal
    		 3.6 28 7.78×
    hyperbolic
    		 2,208 17,577 7.96×
    logmath
    		 3,468 27,661 7.98×
    matrix
    		 2,718 21,586 7.94×
    matrix-3d
    		 632.49 3,141 4.97×
    monte-carlo
    		 85.32 683.11 8.01×
    mpfr
    		 1,012 8,046 7.95×
    powmath
    		 1,209 9,636 7.97×
    trig
    		 1,406 11,257 8.01×
    veccmp
    		 14,882 118,663 7.97×
    vecfp
    		 1,094 8,711 7.96×
    vecmath
    		 2,352 18,722 7.96×
    vecshuf
    		 476.48 3,799 7.97×
    vecwide
    		 22,852 181,863 7.96×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 5.8 46.4 8.00×
    bsearch
    		 176.51 1,412 8.00×
    bubblesort
    		 0.6 4.8 8.00×
    fibsearch
    		 207.66 1,655 7.97×
    heapsort
    		 6.6 52.8 8.00×
    hsearch
    		 5,239 40,688 7.77×
    insertionsort
    		 7.4 59.2 8.00×
    malloc
    		 2,000,180 15,472,047 7.74×
    mcontend
    		 109.3 1,289 11.79×
    mergesort
    		 19.2 153.2 7.98×
    qsort
    		 14.8 118.4 8.00×
    skiplist
    		 3,899 30,997 7.95×
    tree
    		 1.2 9.2 7.67×
    MemorySingleMultiScaling
    cache
    		 329,082 539,205 1.64×
    cachehammer
    		 362,074 2,785,446 7.69×
    cacheline
    		 43.42 362.67 8.35×
    l1cache
    		 658.96 5,232 7.94×
    memcpy
    		 292.13 2,323 7.95×
    memrate
    		 1.56 9.35 5.99×
    memthrash
    		 95.53 365.32 3.82×
    ptr-chase
    		 37,392,787 106,378,307 2.84×
    spinmem
    		 331.39 597.07 1.80×
    stream
    		 38.39 1,845 48.06×
    vm
    		 59,703 292,004 4.89×

    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

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    G3 FAQs