g2-standard-8 by Google Cloud Platform

g2-standard-8 is a Graphics Optimized: 1 NVIDIA L4 GPU, 8 vCPUs, 32GB RAM server offered by Google Cloud Platform with 8 vCPUs, 32 GiB of memory and 0 GB of storage. The pricing starts at 0.3742 USD per hour.
8 vCPU
32 GiB Memory
1 GPU
Spare SCore
6,312
(All-cores)
1,201
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1600008
Name
g2-standard-8
Description
Graphics Optimized: 1 NVIDIA L4 GPU, 8 vCPUs, 32GB RAM
Family
g2
Hw Virt
Average Time To Start
19
Status
active
Observed At
2026-09-21T02:54:47.837587

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.4539 USD/h 0.8508 USD/h
Council Bluffs (US) / us-central1
0.5121 USD/h 0.8536 USD/h
The Dalles (US) / us-west1
0.5121 USD/h 0.8536 USD/h
Moncks Corner (US) / us-east1
0.5121 USD/h 0.8536 USD/h
Mumbai (IN) / asia-south1
0.4526 USD/h 0.8886 USD/h
Eemshaven (NL) / europe-west4
0.5383 USD/h 0.8972 USD/h
St. Ghislain (BE) / europe-west1
0.521 USD/h 0.9399 USD/h
Montréal (CA) / northamerica-northeast1
0.5625 USD/h 0.9399 USD/h
Toronto (CA) / northamerica-northeast2
0.5638 USD/h 0.9399 USD/h
Las Vegas (US) / us-west4
0.5769 USD/h 0.9614 USD/h
London (GB) / europe-west2
0.5832 USD/h 0.9719 USD/h
Changhua County (TW) / asia-east1
0.5639 USD/h 0.9884 USD/h
Frankfurt (DE) / europe-west3
0.6006 USD/h 1.006 USD/h
Jurong West (SG) / asia-southeast1
0.6319 USD/h 1.0531 USD/h
Seoul (KR) / asia-northeast3
0.3742 USD/h 1.0962 USD/h
Tokyo (JP) / asia-northeast1
0.656 USD/h 1.0962 USD/h
Zurich (CH) / europe-west6
0.6991 USD/h 1.1681 USD/h
Dammam (SA) / me-central2
0.7376 USD/h 1.3658 USD/h

Processor

vCPUs
8
CPU Allocation
Dedicated
CPU Cores
4
CPU Speed
2.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
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
39 MiB
CPU L3 Cache Total
39 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, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, fsgsbase, tsc_adjust, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, mpx, avx512f, avx512dq, rdseed, adx, smap, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, arat, avx512_vnni, md_clear, arch_capabilities
Ecpus
5.3
Scalability
132.5

System Resources and Accelerators

MEMORY
Memory Amount
32 GiB
Memory Amount Actual
32 GiB
GPU
GPU Count
1
GPU Memory Min
24 GiB
GPU Memory Total
24 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ada Lovelace
GPU Model
L4
GPUs
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 590.48.01, BIOS version: 95.04.29.00.07, Clock rate: 2040)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    An accelerator-focused virtual machine pairing an NVIDIA L4 GPU with dedicated Intel Xeon processors for efficient machine learning inference.

    GPU AcceleratedGeneral Purpose

    Google Cloud Platform g2-standard-8 is a graphics-optimized server featuring an Intel Xeon x86_64 processor with 8 dedicated vCPUs, 32.0 GB of system memory, and a bundled NVIDIA L4 GPU with 24 GB of VRAM. The instance does not include local storage. Benchmark data reveals a significant performance divergence: while CPU-bound metrics like Geekbench and stress-ng fall into the bottom 25%, the server achieves top-tier performance in LLM inference, processing 2,225.82 tokens per second for a medium 7B model prompt. Memory bandwidth and database operations perform in the average tier. Qualitatively, the server's cost efficiency is optimized for GPU-centric workloads rather than general CPU compute. It is best suited for machine learning inference, small-to-medium LLM deployment, and graphics-accelerated applications where GPU acceleration offsets the weaker CPU performance.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.414Score
    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) 625,875 ops/sec 1,919,696 ops/sec 0.326 50.00% 50.00% -42.90%
    Redis RPS (pipeline=16, SET) 3,989,786 ops/sec 11,736,081 ops/sec 0.34 20.00% 20.00% -19.40%
    PassMark Memory Mark (composite) 2,346 2,418 0.97 10.00% 10.00% -0.30%
    Memory bandwidth (read, 16 MB ~ L3) 54,722 MB/sec 108,260 MB/sec 0.505 10.00% 10.00% -6.60%
    PassMark single-thread CPU 1,695 Mops/s 2,365 Mops/s 0.717 10.00% 10.00% -3.27%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,059

    Geekbench Multi-Core

    Score: 4,017

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 7245
    Compression
    		 94348
    Encryption
    		 2898
    Extended Instructions
    		 5897
    Floating Point Maths
    		 11296
    Integer Maths
    		 21135
    Physics
    		 891
    Prime Numbers
    		 46
    Single Threaded
    		 1695
    String Sorting
    		 11158

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2346
    Database Operations
    		 2657
    Memory Latency
    		 52
    Memory Read Cached
    		 20886
    Memory Read Uncached
    		 11197
    Memory Write
    		 10115

    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

    INSTANCEvCPUsMEMORYGPUs
    g2-standard-4 416 GiB1
    g2-standard-12 1248 GiB1
    g2-standard-16 1664 GiB1
    g2-standard-24 2496 GiB2
    g2-standard-32 32128 GiB1
    g2-standard-48 48192 GiB4
    g2-standard-96 96384 GiB8

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    g2-standard-8 FAQs