vcg-a16-12c-128g-32vram by Vultr

vcg-a16-12c-128g-32vram is a Cloud GPU (12 vCPUs, 128.0 GiB RAM, 700 GB NVMe, 2xA16 16 GiB VRAM) server offered by Vultr with 12 vCPUs, 128 GiB of memory and 700 GB of storage. The pricing starts at 0.942 USD per hour.
12 vCPU
128 GiB Memory
700 GB Storage
2 GPU
Spare SCore
21,081
(All-cores)
1,755
(Single-core)

Specifications

Server Metadata

Vendor ID
vultr
Name
vcg-a16-12c-128g-32vram
Description
Cloud GPU (12 vCPUs, 128.0 GiB RAM, 700 GB NVMe, 2xA16 16 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
101
Status
active
Observed At
2026-09-03T23:38:57.442701

Availability

REGION / IDSPOTONDEMAND
Bangalore (IN) / blr
- 0.942 USD/h

Processor

vCPUs
12
CPU Allocation
Dedicated
CPU Cores
6
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
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, 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
12
Scalability
200

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 GiB
GPU
GPU Count
2
GPU Memory Min
16 GiB
GPU Memory Total
32 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ampere
GPU Model
A16
GPUs
    STORAGE
    Storage Size
    700 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 dual-GPU virtual server featuring dedicated Intel processors, high-capacity system memory, and fast local NVMe storage for accelerated workloads.

      GPU AcceleratedMemory OptimizedStorage & Database

      Vultr vcg-a16-12c-128g-32vram is a GPU-accelerated server instance designed for memory-intensive and parallel computing workloads. It features 12 dedicated Intel vCPUs (6 physical cores) running at 2.0 GHz, 128.0 GB of system memory, and a 700 GB NVMe SSD. The instance is equipped with two NVIDIA Ampere A16 GPUs, delivering a total of 32 GB of VRAM. In benchmark testing, the server demonstrates top-tier performance in LLM prompt processing, reaching 8,665.1 tokens per second for a 135M model and 613.27 tokens per second for a 7B model. General CPU and memory benchmarks, including a Geekbench multi-core score of 9,569.0 and a Passmark CPU score of 20,085.48, fall within the average range. This configuration is highly suitable for small-to-medium language model inference, image processing, ray tracing, and database operations requiring local NVMe storage.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.998Score
      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) 1,815,455 ops/sec 1,917,397 ops/sec 0.947 50.00% 50.00% -2.69%
      Redis RPS (pipeline=16, SET) 12,609,459 ops/sec 11,681,410 ops/sec 1.08 20.00% 20.00% +1.55%
      PassMark Memory Mark (composite) 2,234 2,418 0.924 10.00% 10.00% -0.79%
      Memory bandwidth (read, 16 MB ~ L3) 135,796 MB/sec 108,140 MB/sec 1.26 10.00% 10.00% +2.34%
      PassMark single-thread CPU 2,262 Mops/s 2,365 Mops/s 0.956 10.00% 10.00% -0.45%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,449

      Geekbench Multi-Core

      Score: 9,569

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 20085
      Compression
      		 252141
      Encryption
      		 7216
      Extended Instructions
      		 17438
      Floating Point Maths
      		 47566
      Integer Maths
      		 59087
      Physics
      		 2831
      Prime Numbers
      		 186
      Single Threaded
      		 2262
      String Sorting
      		 34879

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2234
      Database Operations
      		 5284
      Memory Latency
      		 69
      Memory Read Cached
      		 22174
      Memory Read Uncached
      		 11180
      Memory Write
      		 8353

      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

      PostgreSQL heavy read-only throughput

      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-a16-12c-128g-32vram FAQs