vcg-a40-1c-5g-2vram by Vultr

vcg-a40-1c-5g-2vram is a Cloud GPU (1 vCPUs, 5.0 GiB RAM, 90 GB NVMe, 0.0417xA40 48 GiB VRAM) server offered by Vultr with 1 vCPUs, 5 GiB of memory and 90 GB of storage. The pricing starts at 0.075 USD per hour.
1 vCPU
5 GiB Memory
90 GB Storage
0.0417 GPU
Spare SCore
1,714
(All-cores)
1,714
(Single-core)

Specifications

Server Metadata

Vendor ID
vultr
Name
vcg-a40-1c-5g-2vram
Description
Cloud GPU (1 vCPUs, 5.0 GiB RAM, 90 GB NVMe, 0.0417xA40 48 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
81.12
Status
active
Observed At
2026-09-04T06:17:39.098402

Availability

REGION / IDSPOTONDEMAND
New Jersey (US) / ewr
- 0.075 USD/h

Processor

vCPUs
1
CPU Allocation
Dedicated
CPU Cores
1
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU L1D Cache
32 KiB
CPU L1D Cache Total
32 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
32 KiB
CPU L2 Cache
4 MiB
CPU L2 Cache Total
4 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, syscall, nx, 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, pti, ssbd, ibrs, ibpb, fsgsbase, bmi1, avx2, smep, bmi2, erms, invpcid, xsaveopt, arat
Ecpus
1
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
5 GiB
Memory Amount Actual
5 GiB
GPU
GPU Count
0.0417
GPU Memory Min
2 GiB
GPU Memory Total
2 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ampere
GPU Model
A40
GPUs
    STORAGE
    Storage Size
    90 GB
    Storage Type
    nvme ssd
    Storages
      NETWORK
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      3072 GB/month
      IPv4
      1

      CPU and System Topology

      Server Description

      A budget-friendly fractional GPU instance featuring dedicated Intel compute and NVIDIA Ampere acceleration for lightweight machine learning inference.

      GPU AcceleratedBurstable & Budget

      Vultr vcg-a40-1c-5g-2vram is a fractional GPU instance designed for lightweight accelerated workloads. It features a single dedicated Intel x86_64 CPU core running at 2.0 GHz, 5.0 GB of system memory, and 90 GB of local NVMe SSD storage. Graphics and compute acceleration are delivered via a fractional NVIDIA Ampere A40 GPU providing 2 GB of VRAM. While general-purpose benchmarks indicate poor multi-core performance, weak memory bandwidth, and low database throughput, the instance demonstrates top-tier performance in lightweight machine learning tasks. Specifically, it achieves 9931.92 tokens/sec for prompt processing on a small 135M LLM and strong prompt processing speeds on a medium 7B model. This configuration represents a highly cost-efficient option for small-scale LLM inference, model prototyping, and single-threaded tasks that require GPU acceleration without the overhead of a full dedicated card.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.145Score
      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) 153,244 ops/sec 1,917,397 ops/sec 0.0799 50.00% 50.00% -71.70%
      Redis RPS (pipeline=16, SET) 1,074,914 ops/sec 11,681,410 ops/sec 0.092 20.00% 20.00% -37.90%
      PassMark Memory Mark (composite) 1,409 2,418 0.583 10.00% 10.00% -5.25%
      Memory bandwidth (read, 16 MB ~ L3) 32,301 MB/sec 108,140 MB/sec 0.299 10.00% 10.00% -11.40%
      PassMark single-thread CPU 2,066 Mops/s 2,365 Mops/s 0.874 10.00% 10.00% -1.34%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,302

      Geekbench Multi-Core

      Score: 1,303

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 1849
      Compression
      		 21138
      Encryption
      		 591
      Extended Instructions
      		 1318
      Floating Point Maths
      		 3978
      Integer Maths
      		 4843
      Physics
      		 260
      Prime Numbers
      		 15
      Single Threaded
      		 2066
      String Sorting
      		 2853

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 1409
      Database Operations
      		 978
      Memory Latency
      		 54
      Memory Read Cached
      		 21768
      Memory Read Uncached
      		 11171
      Memory Write
      		 10338

      LLM Inference Speed for Prompt Processing

      LLM Inference Speed for Text Generation

      Static Web Server

      Redis

      PostgreSQL heavy read-only throughput

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYGPUs
      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
      vcg-a16-12c-128g-32vram 12128 GiB2

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYGPUs

      vcg-a40-1c-5g-2vram FAQs