m8g.2xlarge
General purpose · AWS Graviton4 (Arm)
Compute
- vCPU
- 8
- Memory
- 32 GiB
- Mem / vCPU
- 4 : 1
Platform
- Family
- m8g
- Architecture
- arm64
- Performance
- Fixed
Cost & region
- On-demand
- $0.3590/hr~$262/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 | 82,092±0.4% | 0.39±0.4% | 1.76±0.2% | 2.15±0.2% | 215,489 | 10,262 | 2,565 |
| 10 GB | gp3-baseline | 81,147±0.6% | 0.39±0.6% | 1.75±0.3% | 2.14±0.1% | 213,009 | 10,143 | 2,536 |
| 1 GB | gp3-max | 71,336±0.4% | 0.45±0.4% | 1.83±0.2% | 2.21±0.1% | 137,729 | 8,917 | 2,229 |
| 10 GB | gp3-max | 71,260±0.3% | 0.45±0.3% | 1.83±0.1% | 2.21±0.1% | 137,582 | 8,907 | 2,227 |
| 50 GB | gp3-max | 26,878±1.1% | 1.19±1.1% | 2.94±1.2% | 3.84±1.3% | 51,894 | 3,360 | 840 |
| 50 GB | gp3-baseline | 5,245±0.7% | 6.10±0.7% | 18.82±13.4% | 27.73±25.2% | 13,768 | 656 | 164 |