Baidu Kunlun P800 Kunlun III vs NVIDIA L40S 48GB

The L40S delivers 5% more FP16 throughput than the Kunlun P800 (362 vs 345 TFLOPS dense).

Kunlun P800: XPU-P (3rd-gen), 2024 L40S: Ada Lovelace, 2023

FP16 dense lead

+5%

L40S: 362 vs 345 TFLOPS

See rental pricing from $0.38/hr Download comparison sheet Printable version →

Baidu Kunlun P800 Kunlun III

Full specs →

What is the Baidu Kunlun P800?

The Kunlun P800 is an NPU from Baidu on the XPU-P (3rd-gen) architecture, an accelerator built for AI inference. Kunlun P800 full specifications →

Can I rent the Kunlun P800 in the cloud?

Flopper is not tracking any live rental listings for the Kunlun P800 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Kunlun P800 compare with other accelerators?

This page sets the Kunlun P800 against the L40S. The Kunlun P800 is the newer generation of the two. This is a cross-vendor matchup, Baidu against NVIDIA. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Kunlun P800 figures come from?

Baidu published the Kunlun P800 figures in marketing material rather than a datasheet, and Flopper has no independent confirmation of them. How Flopper verifies specifications →

NVIDIA L40S 48GB

Leads on FP16 Full specs →

What is the NVIDIA L40S?

The L40S is a GPU from NVIDIA on the Ada Lovelace 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. L40S full specifications →

Can I rent the L40S in the cloud?

Yes. Cloud providers tracked by Flopper rent the L40S by the hour, and the pricing page compares their current rates and the price history side by side. L40S rental prices →

How does the L40S compare with other accelerators?

This page sets the L40S against the Kunlun P800. The L40S is the older generation of the two. This is a cross-vendor matchup, NVIDIA against Baidu. Flopper also compares it head to head with the TPU v5e 16GB and ATOM-Max, across every published precision, memory and power. L40S vs TPU v5e 16GB →

Where do the L40S figures come from?

Every L40S figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

Kunlun P800

L40S

Architecture

XPU-P (3rd-gen)Ada Lovelace

Launch Year

20242023

Form Factor

—PCIe

Memory

—48 GB

Memory Bandwidth

—864 GB/s

TDP

—350 W

Process Node

7nm4nm

Spec

Kunlun P800

L40S

Architecture XPU-P (3rd-gen)Ada Lovelace

Launch Year 20242023

Form Factor —PCIe

Memory —48 GB

Memory Bandwidth —864 GB/s

TDP —350 W

Process Node 7nm4nm

Performance (TFLOPS)

Kunlun P800

L40S

1.4 TFLOPS

92 TFLOPS

183 TFLOPS

366 TFLOPS sparse

362 TFLOPS

733 TFLOPS sparse

345 TFLOPS 362 TFLOPS

733 TFLOPS sparse

733 TFLOPS

1,466 TFLOPS sparse

FP6

733 TOPS

1,466 TOPS sparse

Precision

Kunlun P800

L40S

1.4 TFLOPS

92 TFLOPS

183 TFLOPS

366 TFLOPS sparse

362 TFLOPS

733 TFLOPS sparse

345 TFLOPS 362 TFLOPS

733 TFLOPS sparse

733 TFLOPS

1,466 TFLOPS sparse

FP6

733 TOPS

1,466 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 Kunlun P800 is the newer part: XPU-P (3rd-gen) (2024) against the L40S's Ada Lovelace (2023).

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 Kunlun P800 faster than the L40S?

At FP16 precision the L40S reaches 362 TFLOPS dense against 345 TFLOPS for the Kunlun P800. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the Kunlun P800 or the L40S?

Choose the L40S for training and high-throughput inference: it has 5% more FP16 throughput than the Kunlun P800.

How much do the Kunlun P800 and the L40S cost to rent?

Live cloud listings tracked by Flopper price no live listings yet for the Kunlun P800, and the L40S from $0.38 per GPU-hour across 24 providers. The rental section on this page links to every provider, rate and the price history for each GPU.

Where to Rent

Baidu Kunlun P800 Kunlun III

No live rental listings tracked for the Kunlun P800 yet.

Browse GPU cloud providers

NVIDIA L40S 48GB

Rent from

$0.38 / GPU-hr

Lowest of 43 live listings across 24 providers · median $1.46

See all L40S 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 → Kunlun P800 full specs L40S full specs Estimate cluster cost in the calculator →

Baidu Kunlun P800 Kunlun III vs NVIDIA L40S 48GB

Baidu Kunlun P800 Kunlun III

What is the Baidu Kunlun P800?

Can I rent the Kunlun P800 in the cloud?

How does the Kunlun P800 compare with other accelerators?

Where do the Kunlun P800 figures come from?

NVIDIA L40S 48GB

What is the NVIDIA L40S?

Can I rent the L40S in the cloud?

How does the L40S compare with other accelerators?

Where do the L40S figures come from?

Specifications

Performance (TFLOPS)

FLOPS by Precision

What actually differs

Frequently asked questions

Is the Kunlun P800 faster than the L40S?

Which should you choose, the Kunlun P800 or the L40S?

How much do the Kunlun P800 and the L40S cost to rent?

Where to Rent

Baidu Kunlun P800 Kunlun III

NVIDIA L40S 48GB

Related comparisons

Get Comparison Updates

Stay Updated on GPU Specs