Flopper.io Flopper.io
AWS logo vs

AWS Trainium2 vs NVIDIA H100 SXM5 80GB

The H100 delivers 52% more FP8 throughput than the Trainium2 (1,979 vs 1,299 TFLOPS dense). The Trainium2 counters with 16 GB more memory (96 GB vs 80 GB).

Trainium2: NeuronCore-v3, 2024 H100: Hopper, 2022
FP8 dense lead
+52%
H100: 1,979 vs 1,299 TFLOPS
Memory
96 vs 80 GB
16 GB more for the Trainium2
Bandwidth
2.9 TB/s vs 3.4 TB/s
H100 moves data faster
See rental pricing from $0.79/hr Download comparison sheet

Share this page

AWS Trainium2 vs NVIDIA H100 SXM5 80GB

A post with this link shows the card on the Image tab as its preview.

Post on X Share on LinkedIn
 Printable version →
AWS logo

AWS Trainium2

Full specs →

What is the AWS Trainium2?

The Trainium2 is an ASIC from AWS on the NeuronCore-v3 architecture, an accelerator built for AI workloads. Trainium2 full specifications →

Can I rent the Trainium2 in the cloud?

Flopper is not tracking any live rental listings for the Trainium2 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Trainium2 compare with other accelerators?

This page sets the Trainium2 against the H100. The Trainium2 is the newer generation of the two. This is a cross-vendor matchup, AWS against NVIDIA. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Trainium2 figures come from?

Every Trainium2 figure on this page traces to AWS's own datasheet or specification table. How Flopper verifies specifications →

NVIDIA H100 SXM5 80GB

Leads on FP8 Full specs →

What is the NVIDIA H100?

The H100 is a GPU from NVIDIA on the Hopper architecture, an accelerator for AI training, inference and high-performance computing. It is an SXM module, the mezzanine format used in dense multi-GPU servers. H100 full specifications →

Can I rent the H100 in the cloud?

Yes. Cloud providers tracked by Flopper rent the H100 by the hour, and the pricing page compares their current rates and the price history side by side. H100 rental prices →

How does the H100 compare with other accelerators?

This page sets the H100 against the Trainium2. The H100 is the older generation of the two. This is a cross-vendor matchup, NVIDIA against AWS. Flopper also compares it head to head with the A100 SXM4 80GB, H200 SXM 141GB and Instinct MI300X 192GB, across every published precision, memory and power. H100 vs A100 SXM4 80GB →

Where do the H100 figures come from?

Every H100 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

AWS logo
Trainium2
H100
Architecture
NeuronCore-v3Hopper
Launch Year
20242022
Form Factor
—SXM
Memory
96 GB80 GB
Memory Bandwidth
2.9 TB/s3.4 TB/s
TDP
—700 W
Process Node
—4nm

Performance (TFLOPS)

AWS logo
Trainium2
H100
No verified data available34 TFLOPS
181 TFLOPS 67 TFLOPS
667 TFLOPS
2,563 TFLOPS sparse
494 TFLOPS
989 TFLOPS sparse
667 TFLOPS
2,563 TFLOPS sparse
990 TFLOPS
1,979 TFLOPS sparse
667 TFLOPS
2,563 TFLOPS sparse
990 TFLOPS
1,979 TFLOPS sparse
1,299 TFLOPS
2,563 TFLOPS sparse
1,979 TFLOPS
3,958 TFLOPS sparse
FP6
No verified data available No verified data available
No verified data available No verified data available
No verified data available1,979 TOPS
3,958 TOPS sparse
Tensor Core
No verified data available67 TFLOPS

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 Trainium2 is the newer part: NeuronCore-v3 (2024) against the H100's Hopper (2022).

The Trainium2 carries 16 GB more memory (96 GB against 80 GB), so larger models fit on one GPU before you shard. Bandwidth is 2.9 TB/s against 3.4 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 FP64, FP32, TF32, BF16, FP16, FP8, INT8, Sparsity and TFLOPS. For how the generations relate, see NVIDIA architectures explained.

Frequently asked questions

Is the Trainium2 faster than the H100?

At FP8 precision the H100 reaches 1,979 TFLOPS dense against 1,299 TFLOPS for the Trainium2. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the Trainium2 or the H100?

Choose the H100 for training and high-throughput inference: it has 52% more FP8 throughput than the Trainium2. Choose the Trainium2 when the model has to fit on one GPU: it carries 16 GB more memory.

Which has more memory, the Trainium2 or the H100?

The Trainium2 carries 96 GB of memory versus 80 GB for the H100. Memory bandwidth is 2.9 TB/s for the Trainium2 and 3.4 TB/s for the H100.

How much do the Trainium2 and the H100 cost to rent?

Live cloud listings tracked by Flopper price no live listings yet for the Trainium2, and the H100 from $0.79 per GPU-hour across 32 providers. The rental section on this page links to every provider, rate and the price history for each GPU.

Where to Rent

AWS logo

AWS Trainium2

No live rental listings tracked for the Trainium2 yet.

Browse GPU cloud providers

NVIDIA H100 SXM5 80GB

Rent from

$0.79 / GPU-hr

Lowest of 68 live listings across 32 providers · median $3.95

See all H100 rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

Get Comparison Updates

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

Open in Full Compare Tool → Trainium2 full specs H100 full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI