vcg-a40-4c-20g-8vram by Vultr

vcg-a40-4c-20g-8vram is a Cloud GPU (4 vCPUs, 20.0 GiB RAM, 360 GB NVMe, 0.1667xA40 48 GiB VRAM) server offered by Vultr with 4 vCPUs, 20 GiB of memory and 360 GB of storage. The last known price was 0.288 USD per hour.
4 vCPU
20 GiB Memory
360 GB Storage
0.1667 GPU
Spare SCore
7,057
(All-cores)
1,785
(Single-core)

Specifications

Server Metadata

Vendor ID
vultr
Name
vcg-a40-4c-20g-8vram
Description
Cloud GPU (4 vCPUs, 20.0 GiB RAM, 360 GB NVMe, 0.1667xA40 48 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
77.67
Status
inactive
Observed At
2026-10-19T08:18:09.854823

Availability

REGION / IDSPOTONDEMAND
New Jersey (US) / ewr
- 0.288 USD/h
Frankfurt (DE) / fra
- 0.288 USD/h
Los Angeles (US) / lax
- 0.288 USD/h
London (GB) / lhr
- 0.288 USD/h
Tokyo (JP) / nrt
- 0.288 USD/h
Singapore (SG) / sgp
- 0.288 USD/h
Sydney (AU) / syd
- 0.288 USD/h

Processor

vCPUs
4
CPU Allocation
Dedicated
CPU Cores
2
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
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
4 MiB
CPU L2 Cache Total
8 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, 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
4
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
20 GiB
Memory Amount Actual
20 GiB
ACCELERATORS
Accelerator Count
0.1667
Accelerator Memory Min
8 GiB
Accelerator Memory Total
8 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ampere
Accelerator Model
A40
Accelerators
    STORAGE
    Storage Size
    360 GB
    Storage Type
    nvme ssd
    Storages
      NETWORK
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      5120 GB/month
      IPv4
      1

      CPU and System Topology

      Server Description

      A fractional GPU instance combining dedicated Intel vCPUs and NVIDIA Ampere acceleration for cost-effective machine learning inference and development.

      GPU AcceleratedGeneral Purpose

      Vultr vcg-a40-4c-20g-8vram is an x86_64 fractional GPU instance configured with 4 dedicated Intel vCPUs running at 2.0 GHz, 20.0 GB of system memory, and a 360 GB NVMe SSD. It features a fractional slice of an NVIDIA Ampere A40 GPU, delivering 8 GB of VRAM. This hardware configuration excels in low-to-medium scale LLM inference, with top-tier benchmark results for 135M and 7B models. General compute performance is average, with a Geekbench single-core score of 1384.0 and a multi-core score of 4549.0. However, the instance exhibits weaker performance in database operations and static web serving. This server is qualitatively cost-efficient for developers requiring GPU acceleration without the expense of a full dedicated GPU, making it suitable for light machine learning inference, image processing, and development workloads.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.46Score
      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) 617,106 ops/sec 1,917,050 ops/sec 0.33 50.00% 50.00% -43.00%
      Redis RPS (pipeline=16, SET) 4,325,325 ops/sec 11,661,818 ops/sec 0.36 20.00% 20.00% -18.00%
      PassMark Memory Mark (composite) 2,219 2,417 0.92 10.00% 10.00% -0.83%
      Memory bandwidth (read, 16 MB ~ L3) 103,072 MB/sec 108,361 MB/sec 0.91 10.00% 10.00% -0.94%
      PassMark single-thread CPU 2,236 Mops/s 2,365 Mops/s 0.92 10.00% 10.00% -0.83%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,384

      Geekbench Multi-Core

      Score: 4,549

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 7273
      Compression
      		 83753
      Encryption
      		 2400
      Extended Instructions
      		 5705
      Floating Point Maths
      		 15742
      Integer Maths
      		 19643
      Physics
      		 1066
      Prime Numbers
      		 63
      Single Threaded
      		 2236
      String Sorting
      		 11564

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2219
      Database Operations
      		 1916
      Memory Latency
      		 51
      Memory Read Cached
      		 23004
      Memory Read Uncached
      		 10806
      Memory Write
      		 8898

      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

      vcg-a40-4c-20g-8vram FAQs