m7i.2xlarge
General purpose · 4th-gen Intel Xeon (x86)
PostgreSQL benchmark results for the m7i.2xlarge AWS EC2 instance with 8 vCPU, 32 GiB RAM, and x86-64 architecture.
Compute
- vCPU
- 8
- Memory
- 32 GiB
- Mem / vCPU
- 4 : 1
Platform
- Family
- m7i
- Architecture
- x86-64
- Performance
- Fixed
Cost & region
- On-demand
- $0.4032/hr~$294/mo
- Region
- us-east-1
Chart
Change the metric and disk to see how the numbers shift as the dataset grows — and where it stops fitting in memory.
Open markers sit past the RAM limit (~24 GB of 32 GiB): the dataset no longer fits in cache, so the working set spills to disk and throughput drops.
All results
6 of 6 rows
| 1 GB | gp3-baseline | 73,190±0.5% | 172,163 | 0.44±0.5% | 1.80±0.2% | 2.18±0.1% | 9,149 | 2,287 |
| 10 GB | gp3-baseline | 71,930±1.0% | 169,201 | 0.44±1.0% | 1.81±0.1% | 2.19±0.3% | 8,991 | 2,248 |
| 1 GB | gp3-max | 77,126±0.4% | 137,210 | 0.41±0.4% | 1.80±0.2% | 2.18±0.3% | 9,641 | 2,410 |
| 10 GB | gp3-max | 76,435±0.1% | 135,979 | 0.42±0.1% | 1.80±0.1% | 2.18±0.1% | 9,554 | 2,389 |
| 50 GB | gp3-max | 26,965±1.8% | 47,972 | 1.19±1.8% | 3.17±1.9% | 4.16±2.0% | 3,371 | 843 |
| 50 GB | gp3-baseline | 5,279±1.0% | 12,417 | 6.06±1.0% | 19.86±20.6% | 28.13±27.3% | 660 | 165 |