Flopper.io Flopper.io

NVIDIA A30 24GB vs NVIDIA A800 PCIe 80GB

The A800 delivers 89% more FP16 throughput than the A30 (312 vs 165 TFLOPS dense). The A800 also carries 56 GB more memory (80 GB vs 24 GB).

A30: Ampere, 2021 A800: Ampere, 2022
FP16 dense lead
+89%
A800: 312 vs 165 TFLOPS
Memory
24 vs 80 GB
56 GB more for the A800
Bandwidth
933 GB/s vs 1.9 TB/s
A800 moves data faster
TDP
165 W vs 300 W
A30 draws 135 W less
See rental pricing from $0.35/hr Download comparison sheet

Share this page

NVIDIA A30 24GB vs NVIDIA A800 PCIe 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 A30 24GB

Full specs →

What is the NVIDIA A30?

The A30 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. A30 full specifications →

Can I rent the A30 in the cloud?

Yes. Cloud providers tracked by Flopper rent the A30 by the hour, and the pricing page compares their current rates and the price history side by side. A30 rental prices →

How does the A30 compare with other accelerators?

This page sets the A30 against the A800. The A30 is the older generation of the two. Both are NVIDIA parts, and both ship as a PCIe card, so they fit the same class of system. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the A30 figures come from?

Every A30 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

NVIDIA A800 PCIe 80GB

Leads on FP16 Full specs →

What is the NVIDIA A800?

The A800 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. A800 full specifications →

Can I rent the A800 in the cloud?

Flopper is not tracking any live rental listings for the A800 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the A800 compare with other accelerators?

This page sets the A800 against the A30. The A800 is the newer generation of the two. Both are NVIDIA parts, and both ship as a PCIe card, so they fit the same class of system. Flopper also compares it head to head with the A800 SXM4, across every published precision, memory and power. A800 vs A800 SXM4 →

Where do the A800 figures come from?

Every A800 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

A30
A800
Architecture
AmpereAmpere
Launch Year
20212022
Form Factor
PCIePCIe
Memory
24 GB80 GB
Memory Bandwidth
933 GB/s1.9 TB/s
TDP
165 W300 W
Process Node
—7nm

Performance (TFLOPS)

A30
A800
5.2 TFLOPS 9.7 TFLOPS
10 TFLOPS 20 TFLOPS
82 TFLOPS
165 TFLOPS sparse
156 TFLOPS
sparse not published
165 TFLOPS
330 TFLOPS sparse
312 TFLOPS
sparse not published
165 TFLOPS
330 TFLOPS sparse
312 TFLOPS
sparse not published
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
330 TOPS
661 TOPS sparse
624 TOPS
sparse not published

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 A800 is the newer part: Ampere (2022) against the A30's Ampere (2021).

The A800 carries 56 GB more memory (80 GB against 24 GB), so larger models fit on one GPU before you shard. Bandwidth is 933 GB/s against 1.9 TB/s, which sets the ceiling on decode speed.

Power is 165 W against 300 W, and at FP32 the A800 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 A30 faster than the A800?

At FP16 precision the A800 reaches 312 TFLOPS dense against 165 TFLOPS for the A30. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the A30 or the A800?

Choose the A800 for training and high-throughput inference: it has 89% more FP16 throughput than the A30. It also carries 56 GB more memory, so larger models fit on one GPU before you shard. The A800 draws 135 W more power, so budget for cooling and power delivery before you commit.

Which has more memory, the A30 or the A800?

The A800 carries 80 GB of memory versus 24 GB for the A30. Memory bandwidth is 933 GB/s for the A30 and 1.9 TB/s for the A800.

How much power do the A30 and the A800 draw?

The A30 is rated at 165 W TDP and the A800 at 300 W. On FP32 throughput per watt, the A800 is the more efficient part.

How much do the A30 and the A800 cost to rent?

Live cloud listings tracked by Flopper price the A30 from $0.35 per GPU-hour across 2 providers, and no live listings yet for the A800. The rental section on this page links to every provider, rate and the price history for each GPU.

Where to Rent

NVIDIA A30 24GB

Rent from

$0.35 / GPU-hr

Lowest of 2 live listings across 2 providers

See all A30 rental prices →

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

NVIDIA A800 PCIe 80GB

No live rental listings tracked for the A800 yet.

Browse GPU cloud providers

Get Comparison Updates

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

Open in Full Compare Tool → A30 full specs A800 full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI