AWS Inferentia vs AWS Trainium3

The Trainium3 delivers 10.5x the FP16 throughput of the Inferentia (671 vs 64 TFLOPS dense). The Trainium3 also carries 136 GB more memory (144 GB vs 8 GB).

Inferentia: NeuronCore-v1, 2018 Trainium3: NeuronCore-v4, 2025

FP16 dense lead

10.5x

Trainium3: 671 vs 64 TFLOPS

Memory

8 vs 144 GB

136 GB more for the Trainium3

Bandwidth

50 GB/s vs 4.9 TB/s

Trainium3 moves data faster

Download comparison sheet Printable version →

AWS Inferentia

Full specs →

What is the AWS Inferentia?

The Inferentia is an ASIC from AWS on the NeuronCore-v1 architecture, an accelerator built for AI workloads. Inferentia full specifications →

Can I rent the Inferentia in the cloud?

Flopper is not tracking any live rental listings for the Inferentia yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Inferentia compare with other accelerators?

This page sets the Inferentia against the Trainium3. The Inferentia is the older generation of the two. Both are AWS parts. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Inferentia figures come from?

Every Inferentia figure on this page traces to AWS's own datasheet or specification table. How Flopper verifies specifications →

AWS Trainium3

Leads on FP16 Full specs →

What is the AWS Trainium3?

The Trainium3 is an ASIC from AWS on the NeuronCore-v4 architecture, an accelerator built for AI workloads. Trainium3 full specifications →

Can I rent the Trainium3 in the cloud?

Flopper is not tracking any live rental listings for the Trainium3 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Trainium3 compare with other accelerators?

This page sets the Trainium3 against the Inferentia. The Trainium3 is the newer generation of the two. Both are AWS parts. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Trainium3 figures come from?

Every Trainium3 figure on this page traces to AWS's own datasheet or specification table. How Flopper verifies specifications →

Specifications

Inferentia

Trainium3

Architecture

NeuronCore-v1NeuronCore-v4

Launch Year

20182025

Form Factor

——

Memory

8 GB144 GB

Memory Bandwidth

50 GB/s4.9 TB/s

TDP

——

Process Node

—3nm

Spec

Inferentia

Trainium3

Architecture NeuronCore-v1NeuronCore-v4

Launch Year 20182025

Form Factor ——

Memory 8 GB144 GB

Memory Bandwidth 50 GB/s4.9 TB/s

TDP ——

Process Node —3nm

Performance (TFLOPS)

Inferentia

Trainium3

183 TFLOPS

671 TFLOPS

2,517 TFLOPS sparse

64 TFLOPS 671 TFLOPS

2,517 TFLOPS sparse

64 TFLOPS 671 TFLOPS

2,517 TFLOPS sparse

2,517 TFLOPS

sparse not published

FP6

2,517 TFLOPS

sparse not published

128 TOPS

Precision

Inferentia

Trainium3

183 TFLOPS

671 TFLOPS

2,517 TFLOPS sparse

64 TFLOPS 671 TFLOPS

2,517 TFLOPS sparse

64 TFLOPS 671 TFLOPS

2,517 TFLOPS sparse

2,517 TFLOPS

sparse not published

FP6

2,517 TFLOPS

sparse not published

128 TOPS

Figures are dense. Where a vendor publishes a figure it sits under the dense one and never decides a winner. Hover any precision for its definition, or read the GPU glossary.

FLOPS by Precision

What actually differs

The Trainium3 is the newer part: NeuronCore-v4 (2025) against the Inferentia's NeuronCore-v1 (2018).

The Trainium3 carries 136 GB more memory (144 GB against 8 GB), so larger models fit on one GPU before you shard. Bandwidth is 50 GB/s against 4.9 TB/s, which sets the ceiling on decode speed.

Weight the FP8 and FP16 rows for LLM work and the FP64 row for HPC.

New to the terms? The glossary explains FP32, TF32, BF16, FP16, FP8, FP4, INT8, Sparsity and TFLOPS.

Frequently asked questions

What is better, the Inferentia or the Trainium3?

The Trainium3, on throughput. At FP16 precision the Trainium3 reaches 671 TFLOPS dense against 64 TFLOPS for the Inferentia. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the Inferentia or the Trainium3?

Choose the Trainium3 for training and high-throughput inference: it has 10.5x the FP16 throughput of the Inferentia. It also carries 136 GB more memory, so larger models fit on one GPU before you shard.

Which has more memory, the Inferentia or the Trainium3?

The Trainium3 carries 144 GB of memory versus 8 GB for the Inferentia. Memory bandwidth is 50 GB/s for the Inferentia and 4.9 TB/s for the Trainium3.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.

Open in Full Compare Tool → Inferentia full specs Trainium3 full specs Estimate cluster cost in the calculator →

AWS Inferentia vs AWS Trainium3

AWS Inferentia

What is the AWS Inferentia?

Can I rent the Inferentia in the cloud?

How does the Inferentia compare with other accelerators?

Where do the Inferentia figures come from?

AWS Trainium3

What is the AWS Trainium3?

Can I rent the Trainium3 in the cloud?

How does the Trainium3 compare with other accelerators?

Where do the Trainium3 figures come from?

Specifications

Performance (TFLOPS)

FLOPS by Precision

What actually differs

Frequently asked questions

What is better, the Inferentia or the Trainium3?

Which should you choose, the Inferentia or the Trainium3?

Which has more memory, the Inferentia or the Trainium3?

Get Comparison Updates

Stay Updated on GPU Specs