← All hardware
AWS Trainium3 (Trn3) logo
hardware Data Center AI Accelerators

AWS Trainium3 (Trn3)

by Amazon Web Services

Amazon's newest 3nm-class training chip, up to 4.4x faster than Trn2.

Pros

  • 4.4x performance and 4x perf/watt vs Trn2
  • Strong cost efficiency for AWS-native training
  • Massive UltraCluster scale-out

Cons

  • AWS-only and Neuron-SDK dependent
  • Mostly offered via Capacity Blocks / contracts, not flat on-demand
  • Smaller third-party ecosystem than CUDA

✓ Where it shines / best for

  • AWS-native teams scaling next-gen model training
  • Cost/efficiency-sensitive large training and inference jobs
  • UltraServer/UltraCluster frontier workloads

✕ Not the best fit for

  • Users needing available-now capacity (preview)
  • On-premises or edge use
  • Stacks that cannot run on the Neuron SDK

Features

  • ✓ AI inference
  • ✓ Data-center scale
  • ✓ LLM
  • ✓ API access
  • ✓ AI Training
  • ✓ Cloud Only
  • ✓ Energy Efficient
  • ✓ Neuron SDK
  • ✓ Next Gen
  • ✓ Preview
  • ✓ 3nm

Pricing

PlanPriceBillingNotes
On-demand (cloud)Not yet publishedhourlyTrn3 (Trainium3) instances announced in preview; will be priced per instance-hour on EC2 once generally available. No public rates yet; cloud-only, not sold as silicon.

Pricing verified from the official source. Prices change often — confirm on the vendor's site before buying.

Specifications

architectureTrainium3, AWS custom ASIC
fp8_per_chip2.52 PFLOPS
perf_per_watt4x vs Trn2 UltraServers
memory_per_chip144 GB HBM3e, 4.9 TB/s
ultraserver_scale144 chips, 362 PFLOPS FP8, 20.7 TB HBM3e
Sponsored

A full review is being generated for this product and will appear here shortly.

Compare with

Compare
Compare