r8g.xlarge
Memory optimized · AWS Graviton4 (Arm)
Compute
- vCPU
- 4
- Memory
- 32 GiB
- Mem / vCPU
- 8 : 1
Platform
- Family
- r8g
- Architecture
- arm64
- Performance
- Fixed
Cost & region
- On-demand
- $0.2090/hr~$153/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 | 64,627±0.6% | 0.49±0.6% | 1.89±0.5% | 2.32±0.6% | 279,821 | 16,157 | 2,020 |
| 10 GB | gp3-baseline | 64,110±0.5% | 0.50±0.5% | 1.88±0.2% | 2.31±0.3% | 277,581 | 16,027 | 2,003 |
| 1 GB | gp3-max | 69,292±0.2% | 0.46±0.2% | 1.87±0.2% | 2.36±1.1% | 188,322 | 17,323 | 2,165 |
| 10 GB | gp3-max | 68,012±0.3% | 0.47±0.3% | 1.87±0.1% | 2.35±0.1% | 184,844 | 17,003 | 2,125 |
| 50 GB | gp3-max | 26,542±1.4% | 1.21±1.4% | 2.34±1.0% | 2.93±0.9% | 72,135 | 6,635 | 829 |
| 50 GB | gp3-baseline | 5,124±0.3% | 6.25±0.3% | 11.23±1.2% | 13.74±0.9% | 22,184 | 1,281 | 160 |