1. Architectural & Silicon Specs Head-to-Head

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

g4dnx86_64
G4DN Accelerated Computing
ProcessorIntel Xeon Family
Clock Speed2.5 GHz
RAM / vCPU4.0 GiB/vCPU
Max Network50 Gbps
Max EBS IOPS40,000
AWS NitroSupported
Min Rate (g4dn.xlarge)$0.5260/hr
Monthly Est.$383.98/mo
Cost per vCPU$0.1315/hr
Cost per GiB RAM$0.0329/hr
CoreMark Benchmark55,463
CoreMark / $105,443
Price IndexLowest Cost
Save 48% vs most expensive
Compute / $ Value100% (Leader)
g5x86_64
G5 Accelerated Computing
ProcessorAMD EPYC 7R32
Clock Speed2.8 GHz
RAM / vCPU4.0 GiB/vCPU
Max Network100 Gbps
Max EBS IOPS80,000
AWS NitroSupported
Min Rate (g5.xlarge)$1.0060/hr
Monthly Est.$734.38/mo
Cost per vCPU$0.2515/hr
Cost per GiB RAM$0.0629/hr
CoreMark Benchmark69,634
CoreMark / $69,219
Price Index100% of highest
Compute / $ Value66% of leader
g6x86_64
G6 Accelerated Computing
ProcessorAMD EPYC 7R13 Processor
Clock Speed2.6 GHz
RAM / vCPU4.0 GiB/vCPU
Max Network100 Gbps
Max EBS IOPS240,000
AWS NitroSupported
Min Rate (g6.xlarge)$0.8048/hr
Monthly Est.$587.50/mo
Cost per vCPU$0.2012/hr
Cost per GiB RAM$0.0503/hr
CoreMark Benchmark83,814
CoreMark / $104,143
Price Index80% of highest
Save 20% vs most expensive
Compute / $ Value99% of leader
inf2x86_64
INF2 Accelerated Computing
ProcessorAMD EPYC 7R13 Processor
Clock Speed2.95 GHz
RAM / vCPU4.0 GiB/vCPU
Max Network100 Gbps
Max EBS IOPS240,000
AWS NitroSupported
Min Rate (inf2.xlarge)$0.7582/hr
Monthly Est.$553.49/mo
Cost per vCPU$0.1895/hr
Cost per GiB RAM$0.0474/hr
CoreMark Benchmark79,657
CoreMark / $105,061
Price Index75% of highest
Save 25% vs most expensive
Compute / $ Value100% 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 TiervCPUMemoryg4dnLinux Rateg5Linux Rateg6Linux Rateinf2Linux Rate
.xlarge416 GB
$0.5260/hr
$384.0/moLowest Cost
$1.0060/hr
$734.4/mo+91%
$0.8048/hr
$587.5/mo+53%
$0.7582/hr
$553.5/mo+44%
.2xlarge832 GB
$0.7520/hr
$549.0/moLowest Cost
$1.2120/hr
$884.8/mo+61%
$0.9776/hr
$713.6/mo+30%
—
.4xlarge1664 GB
$1.2040/hr
$878.9/moLowest Cost
$1.6240/hr
$1185.5/mo+35%
$1.3232/hr
$965.9/mo+10%
—
.8xlarge32128 GB
$2.1760/hr
$1588.5/mo+11%
$2.4480/hr
$1787.0/mo+24%
$2.0144/hr
$1470.5/mo+2%
$1.9679/hr
$1436.5/moLowest Cost
.12xlarge48192 GB
$3.9120/hr
$2855.8/moLowest Cost
$5.6720/hr
$4140.6/mo+45%
$4.6016/hr
$3359.2/mo+18%
—
.16xlarge64256 GB
$4.3520/hr
$3177.0/mo+28%
$4.0960/hr
$2990.1/mo+21%
$3.3968/hr
$2479.7/moLowest Cost
—
.24xlarge96384 GB—
$8.1440/hr
$5945.1/mo+25%
$6.6752/hr
$4872.9/mo+3%
$6.4906/hr
$4738.2/moLowest Cost
.48xlarge192768 GB—
$16.2880/hr
$11890.2/mo+25%
$13.3504/hr
$9745.8/mo+3%
$12.9813/hr
$9476.3/moLowest Cost

3. Workload Decision Framework

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

Recommended:G6 (NVIDIA L4) or G5 (A10G)
When: Serving PyTorch/HuggingFace LLMs and diffusion models with standard CUDA software stacks
Why: Ada Lovelace architecture with FP8 precision support and extensive CUDA library maturity.
Recommended:Inf2 (Inferentia2)
When: High-volume production LLM serving where models can be compiled with AWS Neuron SDK
Why: Up to 50% lower cost per inference compared to comparable GPU instances.
Recommended:G4dn (NVIDIA T4)
When: Low-cost legacy inference or video transcoding pipelines
Why: Cost-effective baseline with hardware-accelerated video encoding/decoding.