vcg-a40-8c-40g-16vram by Vultr

vcg-a40-8c-40g-16vram is a Cloud GPU (8 vCPUs, 40.0 GiB RAM, 740 GB NVMe, 0.3333xA40 48 GiB VRAM) server offered by Vultr with 8 vCPUs, 40 GiB of memory and 740 GB of storage. The last known price was 0.575 USD per hour.
8 vCPU
40 GiB Memory
740 GB Storage
0.3333 GPU
Spare SCore
14,175
(All-cores)
1,787
(Single-core)

Specifications

Server Metadata

Vendor ID
vultr
Name
vcg-a40-8c-40g-16vram
Description
Cloud GPU (8 vCPUs, 40.0 GiB RAM, 740 GB NVMe, 0.3333xA40 48 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
69
Status
inactive
Observed At
2026-10-18T21:51:50.818162

Availability

REGION / IDSPOTONDEMAND
Frankfurt (DE) / fra
- 0.575 USD/h
London (GB) / lhr
- 0.575 USD/h
Tokyo (JP) / nrt
- 0.575 USD/h
Singapore (SG) / sgp
- 0.575 USD/h
Sydney (AU) / syd
- 0.575 USD/h

Processor

vCPUs
8
CPU Allocation
Dedicated
CPU Cores
4
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU L1D Cache
32 KiB
CPU L1D Cache Total
256 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
256 KiB
CPU L2 Cache
4 MiB
CPU L2 Cache Total
16 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
7.9
Scalability
98.75

System Resources and Accelerators

MEMORY
Memory Amount
40 GiB
Memory Amount Actual
40 GiB
ACCELERATORS
Accelerator Count
0.3333
Accelerator Memory Min
16 GiB
Accelerator Memory Total
16 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ampere
Accelerator Model
A40
Accelerators
    STORAGE
    Storage Size
    740 GB
    Storage Type
    nvme ssd
    Storages
      NETWORK
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      8192 GB/month
      IPv4
      1

      CPU and System Topology

      Server Description

      A cost-effective fractional GPU server featuring NVIDIA Ampere acceleration and NVMe storage for medium-scale machine learning and inference workloads.

      GPU AcceleratedGeneral PurposeStorage & Database

      Vultr vcg-a40-8c-40g-16vram is a Cloud GPU server designed for accelerated workloads. It features 8 dedicated Intel x86_64 vCPUs operating at 2.0 GHz, 40.0 GB of system memory, and a 740 GB NVMe SSD. Acceleration is delivered via a fractional NVIDIA Ampere A40 GPU with 16 GB of VRAM. While general CPU and memory benchmarks sit in the average tier, the instance delivers top-tier performance in LLM inference, processing 3,147.67 tokens/sec on a medium 7B model. This fractional GPU configuration provides a cost-effective entry point for machine learning and data processing tasks. It is highly suited for small to medium LLM inference, model prototyping, and database operations.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.73Score
      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) 1,212,576 ops/sec 1,917,050 ops/sec 0.63 50.00% 50.00% -21.00%
      Redis RPS (pipeline=16, SET) 8,521,298 ops/sec 11,661,818 ops/sec 0.71 20.00% 20.00% -6.60%
      PassMark Memory Mark (composite) 2,190 2,417 0.92 10.00% 10.00% -0.83%
      Memory bandwidth (read, 16 MB ~ L3) 106,003 MB/sec 108,361 MB/sec 1 10.00% 10.00% 0.00%
      PassMark single-thread CPU 2,279 Mops/s 2,365 Mops/s 0.96 10.00% 10.00% -0.41%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,363

      Geekbench Multi-Core

      Score: 7,229

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 14091
      Compression
      		 174552
      Encryption
      		 4817
      Extended Instructions
      		 11615
      Floating Point Maths
      		 31322
      Integer Maths
      		 39430
      Physics
      		 2083
      Prime Numbers
      		 126
      Single Threaded
      		 2279
      String Sorting
      		 23464

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2190
      Database Operations
      		 3659
      Memory Latency
      		 65
      Memory Read Cached
      		 22208
      Memory Read Uncached
      		 9366
      Memory Write
      		 10040

      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-a40-8c-40g-16vram FAQs