logo

g2-standard-48 by Google Cloud Platform

g2-standard-48 is a Graphics Optimized: 4 NVIDIA L4 GPUs, 48 vCPUs, 192GB RAM server offered by Google Cloud Platform with 48 vCPUs, 192 GiB of memory and 0 GB of storage. The pricing starts at 0.7428 USD per hour.
48 vCPU
192 GiB Memory
4 GPU
Spare SCore
37916
(All-cores)
1196
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1600048
Name
g2-standard-48
Description
Graphics Optimized: 4 NVIDIA L4 GPUs, 48 vCPUs, 192GB RAM
Family
g2
Hw Virt
Average Time To Start
23
Status
active
Observed At
2026-08-07T17:38:41.208648

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.8515 USD/h 1.7557 USD/h
Council Bluffs (US) / us-central1
1.0398 USD/h 1.7615 USD/h
The Dalles (US) / us-west1
1.0398 USD/h 1.7615 USD/h
Moncks Corner (US) / us-east1
1.0398 USD/h 1.7615 USD/h
Mumbai (IN) / asia-south1
0.8895 USD/h 1.8336 USD/h
Eemshaven (NL) / europe-west4
1.0687 USD/h 1.8514 USD/h
St. Ghislain (BE) / europe-west1
0.98 USD/h 1.9396 USD/h
Montréal (CA) / northamerica-northeast1
1.1251 USD/h 1.9396 USD/h
Toronto (CA) / northamerica-northeast2
1.1476 USD/h 1.9396 USD/h
Las Vegas (US) / us-west4
1.1905 USD/h 1.984 USD/h
London (GB) / europe-west2
1.2034 USD/h 2.0056 USD/h
Changhua County (TW) / asia-east1
1.0607 USD/h 2.0396 USD/h
Frankfurt (DE) / europe-west3
1.2456 USD/h 2.076 USD/h
Jurong West (SG) / asia-southeast1
1.3041 USD/h 2.1732 USD/h
Seoul (KR) / asia-northeast3
0.7428 USD/h 2.2621 USD/h
Tokyo (JP) / asia-northeast1
1.3572 USD/h 2.2621 USD/h
Zurich (CH) / europe-west6
1.3845 USD/h 2.3077 USD/h
Dammam (SA) / me-central2
1.6106 USD/h 2.8184 USD/h

Processor

vCPUs
48
CPU Allocation
Dedicated
CPU Cores
24
CPU Speed
2.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
768 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
24 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
31.7
Scalability
132.08

System Resources and Accelerators

MEMORY
Memory Amount
192 GiB
Memory Amount Actual
192 GiB
GPU
GPU Count
4
GPU Memory Min
22 GiB
GPU Memory Total
90 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)
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 590.48.01, BIOS version: 95.04.29.00.07, Clock rate: 2040)
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 590.48.01, BIOS version: 95.04.29.00.07, Clock rate: 2040)
  • 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

    A quad-GPU accelerated server featuring Ada Lovelace architecture and 48 dedicated vCPUs, optimized for high-throughput language model inference.

    GPU AcceleratedGeneral Purpose

    Google Cloud Platform g2-standard-48 is a graphics-optimized server equipped with 4 NVIDIA L4 GPUs from the Ada Lovelace architecture, delivering 90 GB of total VRAM. The host system features 48 dedicated Intel Xeon vCPUs (24 physical cores) operating at 2.2 GHz and 192.0 GB of system memory, with no local storage included. Performance benchmarks indicate a significant divergence: single-core CPU capabilities are weak, ranking in the bottom 25%, while multi-core and memory bandwidth metrics remain average. However, the server achieves top-tier results in LLM inference, particularly for prompt processing and text generation across small, medium, and large models. This hardware profile is highly efficient for parallelized GPU workloads, machine learning inference, and graphics rendering, though it presents a tradeoff for applications reliant on high single-threaded CPU performance or local storage.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    1.46Score
    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) 3,421,975 ops/sec 1,910,660 ops/sec 1.79 50.00% 50.00% +33.80%
    Redis RPS (pipeline=16, SET) 20,098,406 ops/sec 11,608,287 ops/sec 1.73 20.00% 20.00% +11.60%
    PassMark Memory Mark (composite) 2,596 2,416 1.07 10.00% 10.00% +0.68%
    Memory bandwidth (read, 16 MB ~ L3) 110,051 MB/sec 107,896 MB/sec 1.02 10.00% 10.00% +0.20%
    PassMark single-thread CPU 1,703 Mops/s 2,364 Mops/s 0.72 10.00% 10.00% -3.23%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,051

    Geekbench Multi-Core

    Score: 10,460

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 31607
    Compression
    		 548320
    Encryption
    		 16611
    Extended Instructions
    		 34890
    Floating Point Maths
    		 67905
    Integer Maths
    		 126890
    Physics
    		 2474
    Prime Numbers
    		 166
    Single Threaded
    		 1703
    String Sorting
    		 61440

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2596
    Database Operations
    		 15027
    Memory Latency
    		 52
    Memory Read Cached
    		 20570
    Memory Read Uncached
    		 10704
    Memory Write
    		 10150

    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-8 832 GiB1
    g2-standard-12 1248 GiB1
    g2-standard-16 1664 GiB1
    g2-standard-24 2496 GiB2
    g2-standard-32 32128 GiB1
    g2-standard-96 96384 GiB8

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    g2-standard-48 FAQs