Silicon Triangle
AWS R6 Generation: R6i vs R6a vs R6g
6th Gen Memory-Optimized Battleground (8:1 RAM-to-vCPU ratio)
Review memory bandwidth and price per gigabyte of RAM for 6th-gen database hosts, Elasticsearch nodes, and distributed cache clusters.
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 Tier | vCPU | Memory | r6iLinux Rate | r6aLinux Rate | r6gLinux Rate |
|---|---|---|---|---|---|
| .medium | 1 | 8 GB | — | — | |
| .large | 2 | 16 GB | |||
| .xlarge | 4 | 32 GB | |||
| .2xlarge | 8 | 64 GB | |||
| .4xlarge | 16 | 128 GB | |||
| .8xlarge | 32 | 256 GB | |||
| .12xlarge | 48 | 384 GB | |||
| .16xlarge | 64 | 512 GB | |||
| .24xlarge | 96 | 768 GB | — | ||
| .32xlarge | 128 | 1,024 GB | — | ||
| .48xlarge | 192 | 1,536 GB | — | — |
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.