1. Architectural & Silicon Specs Head-to-Head

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

r6ix86_64
R6I Memory Optimized
ProcessorIntel Xeon 8375C (Ice Lake)
Clock Speed3.5 GHz
RAM / vCPU8.0 GiB/vCPU
Max Network50 Gbps
Max EBS IOPS160,000
AWS NitroSupported
Min Rate (r6i.xlarge)$0.2520/hr
Monthly Est.$183.96/mo
Cost per vCPU$0.0630/hr
Cost per GiB RAM$0.0079/hr
CoreMark Benchmark66,127
CoreMark / $262,409
Price Index100% of highest
Compute / $ Value43% of leader
r6ax86_64
R6A Memory Optimized
ProcessorAMD EPYC 7R13 Processor
Clock Speed3.6 GHz
RAM / vCPU8.0 GiB/vCPU
Max Network50 Gbps
Max EBS IOPS240,000
AWS NitroSupported
Min Rate (r6a.xlarge)$0.1430/hr
Monthly Est.$104.39/mo
Cost per vCPU$0.0357/hr
Cost per GiB RAM$0.0045/hr
CoreMark Benchmark79,169
CoreMark / $553,629
Price Index57% of highest
Save 43% vs most expensive
Compute / $ Value91% of leader
r6gARM64 (Graviton)
R6G Memory Optimized
ProcessorAWS Graviton2 Processor
Clock Speed2.5 GHz
RAM / vCPU8.0 GiB/vCPU
Max Network25 Gbps
Max EBS IOPS80,000
AWS NitroSupported
Min Rate (r6g.xlarge)$0.1300/hr
Monthly Est.$94.90/mo
Cost per vCPU$0.0325/hr
Cost per GiB RAM$0.0041/hr
CoreMark Benchmark79,507
CoreMark / $611,592
Price IndexLowest Cost
Save 48% vs most expensive
Compute / $ Value100% (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 TiervCPUMemoryr6iLinux Rater6aLinux Rater6gLinux Rate
.medium18 GB——
$0.0325/hr
$23.7/moLowest Cost
.large216 GB
$0.1260/hr
$92.0/mo+94%
$0.0715/hr
$52.2/mo+10%
$0.0650/hr
$47.5/moLowest Cost
.xlarge432 GB
$0.2520/hr
$184.0/mo+94%
$0.1430/hr
$104.4/mo+10%
$0.1300/hr
$94.9/moLowest Cost
.2xlarge864 GB
$0.5040/hr
$367.9/mo+94%
$0.2860/hr
$208.8/mo+10%
$0.2600/hr
$189.8/moLowest Cost
.4xlarge16128 GB
$1.0080/hr
$735.8/mo+94%
$0.5720/hr
$417.6/mo+10%
$0.5200/hr
$379.6/moLowest Cost
.8xlarge32256 GB
$2.0160/hr
$1471.7/mo+94%
$1.1440/hr
$835.1/mo+10%
$1.0400/hr
$759.2/moLowest Cost
.12xlarge48384 GB
$3.0240/hr
$2207.5/mo+94%
$1.7160/hr
$1252.7/mo+10%
$1.5600/hr
$1138.8/moLowest Cost
.16xlarge64512 GB
$4.0320/hr
$2943.4/mo+94%
$2.2880/hr
$1670.2/mo+10%
$2.0800/hr
$1518.4/moLowest Cost
.24xlarge96768 GB
$6.0480/hr
$4415.0/mo+76%
$3.4320/hr
$2505.4/moLowest Cost
—
.32xlarge1281,024 GB
$8.0640/hr
$5886.7/mo+76%
$4.5760/hr
$3340.5/moLowest Cost
—
.48xlarge1921,536 GB—
$6.8640/hr
$5010.7/moLowest Cost
—

3. Workload Decision Framework

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

Recommended:R6g (Graviton2)
When: High-capacity Redis, Valkey, and Memcached deployments
Why: Significantly lowers memory cost with excellent network packet throughput.
Recommended:R6a (AMD Milan)
When: x86 memory-heavy workloads requiring cost optimization without ARM migration
Why: Reliable 10% savings on large-scale memory clusters compared to R6i.

5. Related Architecture Comparisons

Explore adjacent generational comparisons and silicon trade-offs.