1. Architectural & Silicon Specs Head-to-Head

Comparing underlying processor microarchitectures, memory ratios, and Nitro generation features using representative xlarge sizing.

c7gARM64 (Graviton)
C7G Compute Optimized
ProcessorAWS Graviton3 Processor
Clock Speed2.5 GHz
RAM / vCPU2.0 GiB/vCPU
Max Network30 Gbps
Max EBS IOPS80,000
AWS NitroSupported
Min Rate (c7g.xlarge)$0.0982/hr
Monthly Est.$71.69/mo
Cost per vCPU$0.0245/hr
Cost per GiB RAM$0.0123/hr
CoreMark Benchmark99,782
CoreMark / $1,016,110
Price IndexLowest Cost
Save 15% vs most expensive
Compute / $ Value100% (Leader)
c7gdARM64 (Graviton)
C7GD Compute Optimized
ProcessorAWS Graviton3 Processor
Clock Speed2.5 GHz
RAM / vCPU2.0 GiB/vCPU
Max Network30 Gbps
Max EBS IOPS80,000
AWS NitroSupported
Min Rate (c7gd.xlarge)$0.1152/hr
Monthly Est.$84.10/mo
Cost per vCPU$0.0288/hr
Cost per GiB RAM$0.0144/hr
CoreMark Benchmark100,484
CoreMark / $872,257
Price Index100% of highest
Compute / $ Value86% of leader

2. Side-by-Side Sizing & Pricing Matrix

Direct price and benchmark comparison across matching instance tiers in the lowest-cost region. Lowest hourly cost in each row is highlighted in green.

Size TiervCPUMemoryc7gLinux Ratec7gdLinux Rate
.medium12 GB
$0.0245/hr
$17.9/moLowest Cost
$0.0288/hr
$21.0/mo+18%
.large24 GB
$0.0491/hr
$35.8/moLowest Cost
$0.0576/hr
$42.0/mo+17%
.xlarge48 GB
$0.0982/hr
$71.7/moLowest Cost
$0.1152/hr
$84.1/mo+17%
.2xlarge816 GB
$0.1963/hr
$143.3/moLowest Cost
$0.2304/hr
$168.2/mo+17%
.4xlarge1632 GB
$0.3926/hr
$286.6/moLowest Cost
$0.4608/hr
$336.4/mo+17%
.8xlarge3264 GB
$0.7853/hr
$573.3/moLowest Cost
$0.9216/hr
$672.8/mo+17%
.12xlarge4896 GB
$1.1779/hr
$859.9/moLowest Cost
$1.3824/hr
$1009.2/mo+17%
.16xlarge64128 GB
$1.5706/hr
$1146.5/moLowest Cost
$1.8432/hr
$1345.5/mo+17%

3. Workload Decision Framework

Clear, actionable rules on when each family wins based on workload profile, runtime language, and licensing boundaries.

Recommended:C7g (EBS only)
When: Stateless microservices or workloads with persistent storage on EBS/S3
Why: Lower hourly price; avoid paying for unused local NVMe drive capacity.
Recommended:C7gd (Local NVMe)
When: High-IOPS temporary scratch space, build artifact caching, or local swap
Why: Microsecond NVMe latency without paying per-IOPS or per-throughput EBS fees.

5. Related Architecture Comparisons

Explore adjacent generational comparisons and silicon trade-offs.