hpc7g.4xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | hpc7g.4xlarge |
Description | High performance computing [AWS Graviton processors] Gen7 4xlarge |
Family | hpc7g |
Hw Virt | |
Status | active |
Observed At | 2026-08-18T22:44:00.082553 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Northern Virgina (US) / us-east-1 | - | 1.6832 USD/h |
Dublin (IE) / eu-west-1 | - | 1.8059 USD/h |
Tokyo (JP) / ap-northeast-1 | - | 2.1117 USD/h |
Processor
vCPUs | 16 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 16 |
CPU Speed | 2.6 GHz |
CPU Architecture | arm64 |
CPU Manufacturer | AWS |
CPU Family | ARMv8 |
CPU Model | Neoverse-V1 |
CPU L1D Cache | 64 KiB |
CPU L1D Cache Total | 1 MiB |
CPU L1I Cache | 64 KiB |
CPU L1I Cache Total | 1 MiB |
CPU L2 Cache | 1 MiB |
CPU L2 Cache Total | 16 MiB |
CPU L3 Cache | 32 MiB |
CPU L3 Cache Total | 32 MiB |
CPU Flags | fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, jscvt, fcma, lrcpc, dcpop, sha3, sm3, sm4, asimddp, sha512, sve, asimdfhm, dit, uscat, ilrcpc, flagm, ssbs, paca, pacg, dcpodp, svei8mm, svebf16, i8mm, bf16, dgh, rng |
Ecpus | 16 |
Scalability | 100 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 128 GiB |
Memory Amount Actual | 126 GiB |
| GPU | |
|---|---|
GPU Count | 0 |
GPU Memory Min | 0 MiB |
GPU Memory Total | 0 MiB |
GPUs |
| STORAGE | |
|---|---|
Storage Size | 0 GB |
Storages |
| NETWORK | |
|---|---|
Network Speed Baseline | 200 Gbps |
Network Speed Max | 200 Gbps |
Network Storage Speed Baseline | 0.087 Gbps |
Network Storage Speed Max | 2.085 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
An ARM64-based parallel computing platform featuring dedicated physical cores, high-speed memory bandwidth, and a baseline network capacity of 200 Gbps.
Amazon Web Services hpc7g.4xlarge is an ARM64 server powered by a 16-core AWS Graviton Neoverse-V1 processor running at 2.6 GHz. Built on the Nitro hypervisor, it provides 16 dedicated physical cores with one thread per core and 128.0 GB of system memory, establishing a 1:8 core-to-RAM ratio. The instance features a 200 Gbps baseline network bandwidth but lacks local storage and GPU accelerators. In benchmark testing, it delivers top-tier memory performance, placing in the top 10% for PassMark memory scores, and strong large-block memory write speeds. However, it exhibits weaker performance in CPU encryption and large-scale LLM inference. This server is configured for network-heavy parallel computing, scientific simulations, and memory-bound HPC workloads.
Economics
Performance
Memory Bandwidth
Compression
OpenSSL
Geekbench Single-Core
Geekbench Multi-Core
Passmark CPU Scores
| BENCHMARK | SCORE |
|---|---|
Mark | 11646 |
Compression | 84717 |
Encryption | 2232 |
Extended Instructions | 15661 |
Floating Point Maths | 75962 |
Integer Maths | 76421 |
Physics | 3929 |
Prime Numbers | 161 |
Single Threaded | 1562 |
String Sorting | 63335 |
Passmark Memory Scores
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 3147 |
Database Operations | 16175 |
Memory Latency | 49 |
Memory Read Cached | 19697 |
Memory Read Uncached | 19060 |
Memory Write | 19714 |
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 |
|---|---|---|---|
| hpc7g.8xlarge | 32 | 128 GiB | 0 |
| hpc7g.16xlarge | 64 | 128 GiB | 0 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|