logo

vcg-a40-12c-60g-24vram by Vultr

vcg-a40-12c-60g-24vram is a Cloud GPU (12 vCPUs, 60.0 GiB RAM, 1110 GB NVMe, 0.5xA40 48 GiB VRAM) server offered by Vultr with 12 vCPUs, 60 GiB of memory and 1.11 TB of storage.
12 vCPU
60 GiB Memory
1.11 TB Storage
0.5 GPU
Spare SCore
20624
(All-cores)
1631
(Single-core)

Specifications

Server Metadata

Vendor ID
vultr
Name
vcg-a40-12c-60g-24vram
Description
Cloud GPU (12 vCPUs, 60.0 GiB RAM, 1110 GB NVMe, 0.5xA40 48 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
172
Status
active
Observed At
2026-07-20T13:40:44.473198

Availability

REGION / IDSPOTONDEMAND

Processor

vCPUs
12
CPU Allocation
Shared
CPU Cores
6
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
384 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
384 KiB
CPU L2 Cache
4 MiB
CPU L2 Cache Total
24 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
16 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, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, cpuid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, cpuid_fault, ssbd, ibrs, ibpb, ibrs_enhanced, fsgsbase, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, arat, pku, ospke, avx512_vnni, arch_capabilities
Ecpus
12.6
Scalability
210

System Resources and Accelerators

MEMORY
Memory Amount
60 GiB
Memory Amount Actual
60 GiB
GPU
GPU Count
0.5
GPU Memory Min
24 GiB
GPU Memory Total
24 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ampere
GPU Model
A40
GPUs
    STORAGE
    Storage Size
    1110 GB
    Storage Type
    nvme ssd
    Storages
      NETWORK
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      10240 GB/month
      IPv4
      1

      CPU and System Topology

      Server Description

      A fractional GPU instance balancing a half-slice NVIDIA A40 GPU with shared Intel Xeon compute and local NVMe storage.

      GPU AcceleratedStorage & DatabaseGeneral Purpose

      Vultr vcg-a40-12c-60g-24vram is a Cloud GPU server featuring a fractional NVIDIA A40 GPU with 24 GB of VRAM, paired with 12 shared Intel Xeon vCPUs running at 2.0 GHz. The system includes 60.0 GB of system memory and 1110 GB of local NVMe SSD storage. Benchmark results show average performance across most categories, including a stress-ng multi-core score of 20624.31 and a PassMark CPU score of 20613.93. LLM inference benchmarks reveal a clear tradeoff: the server processes small 135M models efficiently at 1048.4 tokens/sec for prompts, but performance drops to a weak 23.45 tokens/sec for medium 7B model prompts. This instance provides a cost-efficient entry point for GPU-accelerated workloads, making it suitable for small-scale machine learning inference, database operations, and general-purpose applications requiring moderate GPU acceleration and local NVMe storage.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      1.2Score
      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) 2,384,515 ops/sec 1,895,870 ops/sec 1.26 50.00% 50.00% +12.20%
      Redis RPS (pipeline=16, SET) 14,181,822 ops/sec 11,503,938 ops/sec 1.23 20.00% 20.00% +4.23%
      PassMark Memory Mark (composite) 2,521 2,410 1.05 10.00% 10.00% +0.49%
      Memory bandwidth (read, 16 MB ~ L3) 138,092 MB/sec 107,331 MB/sec 1.29 10.00% 10.00% +2.58%
      PassMark single-thread CPU 2,262 Mops/s 2,363 Mops/s 0.957 10.00% 10.00% -0.44%

      Memory Bandwidth

      Compression

      OpenSSL

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		20614
      Compression
      		261673
      Encryption
      		7232
      Extended Instructions
      		22214
      Floating Point Maths
      		45296
      Integer Maths
      		59181
      Physics
      		2910
      Prime Numbers
      		185
      Single Threaded
      		2262
      String Sorting
      		35593

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		2521
      Database Operations
      		5564
      Memory Latency
      		55
      Memory Read Cached
      		22540
      Memory Read Uncached
      		10794
      Memory Write
      		10616

      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
      vcg-a40-1c-5g-2vram 15 GiB1⁄24
      vcg-a40-2c-10g-4vram 210 GiB1⁄12
      vcg-a16-2c-8g-2vram 28 GiB⅛
      vcg-a16-2c-16g-4vram 216 GiB¼
      vcg-a16-3c-32g-8vram 332 GiB½
      vcg-a40-4c-20g-8vram 420 GiB⅙
      vcg-a40-6c-30g-12vram 630 GiB¼

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYGPUs

      vcg-a40-12c-60g-24vram FAQs