Flopper.io Flopper.io

NVIDIA V100 SXM2 32GB vs NVIDIA V100S PCIe 32GB

The V100S delivers 4% more FP16 throughput than the V100 (130 vs 125 TFLOPS dense).

V100: Volta, 2018 V100S: Volta, 2020
FP16 dense lead
+4%
V100S: 130 vs 125 TFLOPS
Memory
32 vs 32 GB
Same capacity
Bandwidth
900 GB/s vs 1.1 TB/s
V100S moves data faster
TDP
300 W vs 250 W
V100S draws 50 W less
See rental pricing from $0.12/hr Download comparison sheet

Share this page

NVIDIA V100 SXM2 32GB vs NVIDIA V100S PCIe 32GB

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

Post on X Share on LinkedIn
 Printable version →

NVIDIA V100 SXM2 32GB

Full specs →

What is the NVIDIA V100?

The V100 is a GPU from NVIDIA on the Volta 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. V100 full specifications →

Can I rent the V100 in the cloud?

Yes. Cloud providers tracked by Flopper rent the V100 by the hour, and the pricing page compares their current rates and the price history side by side. V100 rental prices →

How does the V100 compare with other accelerators?

This page sets the V100 against the V100S. The V100 is the older generation of the two. Both are NVIDIA parts; the V100 is an SXM module while the V100S is a PCIe card. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the V100 figures come from?

Every V100 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

NVIDIA V100S PCIe 32GB

Leads on FP16 Full specs →

What is the NVIDIA V100S?

The V100S is a GPU from NVIDIA on the Volta 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. V100S full specifications →

Can I rent the V100S in the cloud?

Yes. Cloud providers tracked by Flopper rent the V100S by the hour, and the pricing page compares their current rates and the price history side by side. V100S rental prices →

How does the V100S compare with other accelerators?

This page sets the V100S against the V100. The V100S is the newer generation of the two. Both are NVIDIA parts; the V100S is a PCIe card while the V100 is an SXM module. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the V100S figures come from?

Every V100S figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

V100
V100S
Architecture
VoltaVolta
Launch Year
20182020
Form Factor
SXMPCIe
Memory
32 GB32 GB
Memory Bandwidth
900 GB/s1.1 TB/s
TDP
300 W250 W
Process Node
12nm12nm

Performance (TFLOPS)

V100
V100S
7.8 TFLOPS 8.2 TFLOPS
16 TFLOPS 16 TFLOPS
No verified data available No verified data available
No verified data available No verified data available
125 TFLOPS 130 TFLOPS
No verified data available No verified data available
FP6
No verified data available No verified data available
No verified data available No verified data available
No verified data available No verified data available

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 V100S is the newer part: Volta (2020) against the V100's Volta (2018).

Both carry 32 GB of memory. Bandwidth is 900 GB/s against 1.1 TB/s, which sets the ceiling on decode speed.

Power is 300 W against 250 W, and at FP32 the V100S 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, FP16, Sparsity and TFLOPS. For how the generations relate, see NVIDIA architectures explained.

Frequently asked questions

Is the V100 faster than the V100S?

At FP16 precision the V100S reaches 130 TFLOPS dense against 125 TFLOPS for the V100. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the V100 or the V100S?

Choose the V100S for training and high-throughput inference: it has 4% more FP16 throughput than the V100. The V100S draws 50 W less power, which matters in an air-cooled or power-capped rack. Packaging differs too: the V100 is an SXM module while the V100S is a PCIe card, so check what your servers accept.

Which has more memory, the V100 or the V100S?

Both GPUs carry 32 GB of memory. Memory bandwidth is 900 GB/s for the V100 and 1.1 TB/s for the V100S.

How much power do the V100 and the V100S draw?

The V100 is rated at 300 W TDP and the V100S at 250 W. On FP32 throughput per watt, the V100S is the more efficient part.

How much do the V100 and the V100S cost to rent?

Live cloud listings tracked by Flopper price the V100 from $0.12 per GPU-hour across 2 providers, and the V100S from $0.13 per GPU-hour across 2 providers. The rental section on this page links to every provider, rate and the price history for each GPU.

Where to Rent

NVIDIA V100 SXM2 32GB

Rent from

$0.12 / GPU-hr

Lowest of 2 live listings across 2 providers

See all V100 rental prices →

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

NVIDIA V100S PCIe 32GB

Rent from

$0.13 / GPU-hr

Lowest of 2 live listings across 2 providers

See all V100S 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 → V100 full specs V100S full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI