Flopper.io Flopper.io

NVIDIA A10 24GB vs NVIDIA A100 SXM4 40GB

The A100 delivers 2.5x the FP16 throughput of the A10 (312 vs 125 TFLOPS dense). The A100 also carries 16 GB more memory (40 GB vs 24 GB).

A10: Ampere, 2021 A100: Ampere, 2020
FP16 dense lead
2.5x
A100: 312 vs 125 TFLOPS
Memory
24 vs 40 GB
16 GB more for the A100
Bandwidth
600 GB/s vs 1.6 TB/s
A100 moves data faster
TDP
150 W vs 400 W
A10 draws 250 W less
See rental pricing from $0.54/hr Download comparison sheet

Share this page

NVIDIA A10 24GB vs NVIDIA A100 SXM4 40GB

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

Post on X Share on LinkedIn
 Printable version →

NVIDIA A10 24GB

Full specs →

What is the NVIDIA A10?

The A10 is a GPU from NVIDIA on the Ampere 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. A10 full specifications →

Can I rent the A10 in the cloud?

Yes. Cloud providers tracked by Flopper rent the A10 by the hour, and the pricing page compares their current rates and the price history side by side. A10 rental prices →

How does the A10 compare with other accelerators?

This page sets the A10 against the A100. The A10 is the newer generation of the two. Both are NVIDIA parts; the A10 is a PCIe card while the A100 is an SXM module. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the A10 figures come from?

Every A10 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

NVIDIA A100 SXM4 40GB

Leads on FP16 Full specs →

What is the NVIDIA A100?

The A100 is a GPU from NVIDIA on the Ampere 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. A100 full specifications →

Can I rent the A100 in the cloud?

Yes. Cloud providers tracked by Flopper rent the A100 by the hour, and the pricing page compares their current rates and the price history side by side. A100 rental prices →

How does the A100 compare with other accelerators?

This page sets the A100 against the A10. The A100 is the older generation of the two. Both are NVIDIA parts; the A100 is an SXM module while the A10 is a PCIe card. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the A100 figures come from?

Every A100 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

A10
A100
Architecture
AmpereAmpere
Launch Year
20212020
Form Factor
PCIeSXM
Memory
24 GB40 GB
Memory Bandwidth
600 GB/s1.6 TB/s
TDP
150 W400 W
Process Node
—7nm

Performance (TFLOPS)

A10
A100
No verified data available9.7 TFLOPS
31 TFLOPS 20 TFLOPS
63 TFLOPS
125 TFLOPS sparse
156 TFLOPS
312 TFLOPS sparse
125 TFLOPS
250 TFLOPS sparse
312 TFLOPS
624 TFLOPS sparse
125 TFLOPS
250 TFLOPS sparse
312 TFLOPS
624 TFLOPS sparse
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
250 TOPS
500 TOPS sparse
624 TOPS
1,248 TOPS sparse

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 A10 is the newer part: Ampere (2021) against the A100's Ampere (2020).

The A100 carries 16 GB more memory (40 GB against 24 GB), so larger models fit on one GPU before you shard. Bandwidth is 600 GB/s against 1.6 TB/s, which sets the ceiling on decode speed.

Power is 150 W against 400 W, and at FP32 the A10 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, INT8, Sparsity and TFLOPS. For how the generations relate, see NVIDIA architectures explained.

Frequently asked questions

Is the A10 faster than the A100?

At FP16 precision the A100 reaches 312 TFLOPS dense against 125 TFLOPS for the A10. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the A10 or the A100?

Choose the A100 for training and high-throughput inference: it has 2.5x the FP16 throughput of the A10. It also carries 16 GB more memory, so larger models fit on one GPU before you shard. The A100 draws 250 W more power, so budget for cooling and power delivery before you commit. Packaging differs too: the A10 is a PCIe card while the A100 is an SXM module, so check what your servers accept.

Which has more memory, the A10 or the A100?

The A100 carries 40 GB of memory versus 24 GB for the A10. Memory bandwidth is 600 GB/s for the A10 and 1.6 TB/s for the A100.

How much power do the A10 and the A100 draw?

The A10 is rated at 150 W TDP and the A100 at 400 W. On FP32 throughput per watt, the A10 is the more efficient part.

How much do the A10 and the A100 cost to rent?

Live cloud listings tracked by Flopper price the A10 from $1.10 per GPU-hour across 4 providers, and the A100 from $0.54 per GPU-hour across 9 providers. The rental section on this page links to every provider, rate and the price history for each GPU.

Where to Rent

NVIDIA A10 24GB

Rent from

$1.10 / GPU-hr

Lowest of 6 live listings across 4 providers · median $1.20

See all A10 rental prices →

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

NVIDIA A100 SXM4 40GB

Rent from

$0.54 / GPU-hr

Lowest of 14 live listings across 9 providers · median $2.05

See all A100 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 → A10 full specs A100 full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI