Skip to content

Benchmarks for i8g.large (AWS)

Individual CPU benchmark results for the AWS EC2 instance type i8g.large. The table displays the single-threaded CPU speed as reported by the Passmark benchmark tool, as well as the on-demand, spot pricing, and spot interruption percentage.

See the benchmarks for all EC2 instances.

✅ This instance type is available for self-hosted GitHub Actions runners using RunsOn.

EC2 Instance family: i8g

CPU Type: Arm-based AWS Graviton4 processors. Specific Features: Storage-optimized instance with 3rd generation AWS Nitro SSDs and DDR5-5600 memory. Ideal for I/O intensive workloads, such as real-time databases and analytics, offering high real-time storage performance and low storage I/O latency. Supports up to 96 vCPUs and 768 GiB of memory, with up to 45 TB of instance storage. Date of Release (General Availability): December 1, 2024.

Results

This benchmark has been generated using the i8g.large instance type. Results are averaged over many days (you can mouse over the sparline to get more details).

🇚ðŸ‡ļ North Virginia (us-east-1)

Family Instance type Processor CPU speed (avg) $/hour on-demand $/hour spot (avg) Spot savings over on-demand Spot % interruption
i8g i8g.large Neoverse-V2 (aarch64) 1914 0.1716 0.0492 49% <5%

🇚ðŸ‡ļ Oregon (us-west-2)

Family Instance type Processor CPU speed (avg) $/hour on-demand $/hour spot (avg) Spot savings over on-demand Spot % interruption
i8g i8g.large Neoverse-V2 (aarch64) 1914 0.1716 0.0714 45% 5-10%

ðŸ‡Ū🇊 Ireland (eu-west-1)

Family Instance type Processor CPU speed (avg) $/hour on-demand $/hour spot (avg) Spot savings over on-demand Spot % interruption
i8g i8g.large Neoverse-V2 (aarch64) 1914 0.1891 0.1222 57% 5-10%

ðŸ‡Đ🇊 Frankfurt (eu-central-1)

Family Instance type Processor CPU speed (avg) $/hour on-demand $/hour spot (avg) Spot savings over on-demand Spot % interruption
i8g i8g.large Neoverse-V2 (aarch64) 1914 0.2046 0.1039 64% <5%

About those benchmarks

Benchmarks are performed using the Passmark benchmarking tool, using the CPU Single Threaded metric.