Flopper.io Flopper.io

NVIDIA H100 NVL 94GB vs NVIDIA H100 SXM5 80GB

The H100 SXM5 80GB delivers 12% more FP32 throughput than the H100 NVL 94GB (67 vs 60 TFLOPS dense). The H100 NVL 94GB counters with 14 GB more memory (94 GB vs 80 GB).

H100 NVL 94GB: Hopper, 2023 H100 SXM5 80GB: Hopper, 2022
FP32 dense lead
+12%
H100 SXM5 80GB: 67 vs 60 TFLOPS
Memory
94 vs 80 GB
14 GB more for the H100 NVL 94GB
Bandwidth
3.9 TB/s vs 3.4 TB/s
H100 NVL 94GB moves data faster
TDP
400 W vs 700 W
H100 NVL 94GB draws 300 W less
See rental pricing from $0.79/hr Download comparison sheet

Share this page

NVIDIA H100 NVL 94GB 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 →

NVIDIA H100 NVL 94GB

Full specs →

What is the NVIDIA H100 NVL 94GB?

The H100 NVL 94GB is a GPU from NVIDIA on the Hopper architecture, an accelerator for AI training, inference and high-performance computing. It is a PCIe add-in card, so it fits standard servers and workstations. H100 NVL 94GB full specifications →

Can I rent the H100 NVL 94GB in the cloud?

Yes. Cloud providers tracked by Flopper rent the H100 NVL 94GB by the hour, and the pricing page compares their current rates and the price history side by side. H100 NVL 94GB rental prices →

How does the H100 NVL 94GB compare with other accelerators?

This page sets the H100 NVL 94GB against the H100 SXM5 80GB. The H100 NVL 94GB is the newer generation of the two. Both are NVIDIA parts; the H100 NVL 94GB is a PCIe card while the H100 SXM5 80GB is an SXM module. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the H100 NVL 94GB figures come from?

Every H100 NVL 94GB figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

NVIDIA H100 SXM5 80GB

Leads on FP32 Full specs →

What is the NVIDIA H100 SXM5 80GB?

The H100 SXM5 80GB 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 SXM5 80GB full specifications →

Can I rent the H100 SXM5 80GB in the cloud?

Yes. Cloud providers tracked by Flopper rent the H100 SXM5 80GB by the hour, and the pricing page compares their current rates and the price history side by side. H100 SXM5 80GB rental prices →

How does the H100 SXM5 80GB compare with other accelerators?

This page sets the H100 SXM5 80GB against the H100 NVL 94GB. The H100 SXM5 80GB is the older generation of the two. Both are NVIDIA parts; the H100 SXM5 80GB is an SXM module while the H100 NVL 94GB is a PCIe card. 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 SXM5 80GB vs A100 SXM4 80GB →

Where do the H100 SXM5 80GB figures come from?

Every H100 SXM5 80GB figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

H100 NVL 94GB
H100 SXM5 80GB
Architecture
HopperHopper
Launch Year
20232022
Form Factor
PCIeSXM
Memory
94 GB80 GB
Memory Bandwidth
3.9 TB/s3.4 TB/s
TDP
400 W700 W
Process Node
4nm4nm

Performance (TFLOPS)

H100 NVL 94GB
H100 SXM5 80GB
30 TFLOPS 34 TFLOPS
60 TFLOPS 67 TFLOPS
The vendor publishes only the 2:4 sparse figure for this precision
835 TFLOPS sparse
494 TFLOPS
989 TFLOPS sparse
The vendor publishes only the 2:4 sparse figure for this precision
1,671 TFLOPS sparse
990 TFLOPS
1,979 TFLOPS sparse
The vendor publishes only the 2:4 sparse figure for this precision
1,671 TFLOPS sparse
990 TFLOPS
1,979 TFLOPS sparse
The vendor publishes only the 2:4 sparse figure for this precision
3,341 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
The vendor publishes only the 2:4 sparse figure for this precision
3,341 TOPS sparse
1,979 TOPS
3,958 TOPS sparse
Tensor Core
60 TFLOPS 67 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 H100 NVL 94GB is the newer part: Hopper (2023) against the H100 SXM5 80GB's Hopper (2022).

The H100 NVL 94GB carries 14 GB more memory (94 GB against 80 GB), so larger models fit on one GPU before you shard. Bandwidth is 3.9 TB/s against 3.4 TB/s, which sets the ceiling on decode speed.

Power is 400 W against 700 W, and at FP32 the H100 NVL 94GB does more work per watt. 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 H100 NVL 94GB faster than the H100 SXM5 80GB?

At FP32 precision the H100 SXM5 80GB reaches 67 TFLOPS dense against 60 TFLOPS for the H100 NVL 94GB. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the H100 NVL 94GB or the H100 SXM5 80GB?

Choose the H100 SXM5 80GB for training and high-throughput inference: it has 12% more FP32 throughput than the H100 NVL 94GB. Choose the H100 NVL 94GB when the model has to fit on one GPU: it carries 14 GB more memory. The H100 SXM5 80GB draws 300 W more power, so budget for cooling and power delivery before you commit. Packaging differs too: the H100 NVL 94GB is a PCIe card while the H100 SXM5 80GB is an SXM module, so check what your servers accept.

Which has more memory, the H100 NVL 94GB or the H100 SXM5 80GB?

The H100 NVL 94GB carries 94 GB of memory versus 80 GB for the H100 SXM5 80GB. Memory bandwidth is 3.9 TB/s for the H100 NVL 94GB and 3.4 TB/s for the H100 SXM5 80GB.

How much power do the H100 NVL 94GB and the H100 SXM5 80GB draw?

The H100 NVL 94GB is rated at 400 W TDP and the H100 SXM5 80GB at 700 W. On FP32 throughput per watt, the H100 NVL 94GB is the more efficient part.

How much do the H100 NVL 94GB and the H100 SXM5 80GB cost to rent?

Live cloud listings tracked by Flopper price the H100 NVL 94GB from $2.59 per GPU-hour across 4 providers, and the H100 SXM5 80GB 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

NVIDIA H100 NVL 94GB

Rent from

$2.59 / GPU-hr

Lowest of 7 live listings across 4 providers · median $3.19

See all H100 NVL 94GB rental prices →

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

NVIDIA H100 SXM5 80GB

Rent from

$0.79 / GPU-hr

Lowest of 65 live listings across 32 providers · median $3.64

See all H100 SXM5 80GB 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 → H100 NVL 94GB full specs H100 SXM5 80GB full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI