vcg-a16-6c-64g-16vram by Vultr
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | vultr |
Name | vcg-a16-6c-64g-16vram |
Description | Dedicated Metal GPU (6 vCPUs, 64.0 GiB RAM, 350 GB NVMe) |
Family | Dedicated Metal GPU |
Hw Virt | |
Average Time To Start | 71.33 |
Status | inactive |
Observed At | 2026-09-03T17:31:49.876151 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|
Processor
vCPUs | 6 |
CPU Allocation | Dedicated |
CPU Cores | 3 |
CPU Speed | 2 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | Intel |
CPU L1D Cache | 32 KiB |
CPU L1D Cache Total | 192 KiB |
CPU L1I Cache | 32 KiB |
CPU L1I Cache Total | 192 KiB |
CPU L2 Cache | 4 MiB |
CPU L2 Cache Total | 12 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 | 6.1 |
Scalability | 203.33 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 64 GiB |
Memory Amount Actual | 64 GiB |
| GPU | |
|---|---|
GPU Count | 0 |
GPU Memory Min | 0 MiB |
GPU Memory Total | 0 MiB |
GPU Manufacturer | NVIDIA |
GPUs |
| STORAGE | |
|---|---|
Storage Size | 350 GB |
Storage Type | nvme ssd |
Storages |
| NETWORK | |
|---|---|
Inbound Traffic | 0 GB/month |
Outbound Traffic | 6144 GB/month |
IPv4 | 1 |
CPU and System Topology
Server Description
A dedicated x86_64 server combining high memory density, local NVMe storage, and strong prompt processing capabilities for memory-intensive workloads.
Vultr vcg-a16-6c-64g-16vram is a dedicated bare metal server from the Dedicated Metal GPU family, featuring 6 dedicated Intel x86_64 vCPUs and 64.0 GB of RAM. It includes a bundled 350 GB NVMe SSD and one public IPv4 address. Performance benchmarks place this instance in the average tier for general compute and memory bandwidth, with stress-ng multi-core scoring 10619.81 and Passmark CPU scoring 10693.5. However, it exhibits top-tier capabilities in LLM inference prompt processing, reaching 591.21 tokens per second on a medium 7B model. With a high memory-to-vCPU ratio of 10.67 GB per core, this server is suited for memory-intensive workloads, caching, database operations, and small-to-medium language model inference.
Economics
Performance
Memory Bandwidth
Compression
OpenSSL
Geekbench Single-Core
Geekbench Multi-Core
Passmark CPU Scores
| BENCHMARK | SCORE |
|---|---|
Mark | 10694 |
Compression | 126012 |
Encryption | 3605 |
Extended Instructions | 8629 |
Floating Point Maths | 23748 |
Integer Maths | 29479 |
Physics | 1499 |
Prime Numbers | 93 |
Single Threaded | 2260 |
String Sorting | 17486 |
Passmark Memory Scores
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 2512 |
Database Operations | 2986 |
Memory Latency | 52 |
Memory Read Cached | 22926 |
Memory Read Uncached | 11468 |
Memory Write | 10622 |
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
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|---|---|---|
| vcg-a40-24c-120g-48vram | 24 | 120 GiB | 0 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|