Nvidia A100 vs Nvidia L40S

The A100 has 67% more memory and 2.2x the bandwidth. The L40S is newer and typically cheaper.

At a glance

Memory

67% more on A100

A100: 80 GB

L40S: 48 GB

Memory bandwidth

2.2x higher on A100

A100: 1,935 GB/s

L40S: 864 GB/s

Cheapest on-demand

14% cheaper on L40S

A100: $0.44 /GPU/hr

L40S: $0.38 /GPU/hr

Price comparison

Median price per GPU per hour by billing type, with the cheapest listing under it.

Billing	A100	L40S	Difference
On-demand	$1.76 /GPU/hr from $0.44	$1.50 /GPU/hr from $0.38	15% cheaper on L40S
Reserved	$1.60 /GPU/hr from $0.64 (12 mo)	$1.10 /GPU/hr from $0.60 (12 mo)	31% cheaper on L40S
Spot	$1.08 /GPU/hr from $0.23	$1.06 /GPU/hr from $0.40	Within 5%

Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. Verify before provisioning. More on how we price.

Price history

A100 vs L40S price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	A100	L40S	Difference
Memory
Capacity	80 GB HBM2e 40 GB on SXM, PCIe	48 GB GDDR6	67% more on A100
Bandwidth	1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe	864 GB/s	2.2x higher on A100
Bus width	5,120-bit	384-bit	13x wider on A100
Compute · dense
FP8	Not supported	733 TFLOPS	L40S only
FP16 / BF16	312 TFLOPS	362.1 TFLOPS	16% higher on L40S
INT8	624 TOPS	733 TOPS	17% higher on L40S
FP32	19.5 TFLOPS	91.6 TFLOPS	4.7x higher on L40S
FP64	9.7 TFLOPS	Not supported	A100 only
Platform
Interconnect	NVLink 600 GB/s	PCIe only	NVLink on A100 only
Board power	300 W	350 W	17% higher on L40S
Released	Q2 2020	Q3 2023	3 years newer on L40S
Precision
Supported formats	FP16BF16TF32FP32FP64INT4INT8	FP8FP16BF16TF32FP32INT4INT8

Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.

Compute: Vendor peak figures, dense and per GPU. Not measured throughput.

Source: A100 datasheet and L40S datasheet.

Where to rent them

Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.

Provider	A100	L40S
Vast.ai USA	$0.44 /GPU/hr On-demand PCIe	$0.73 /GPU/hr On-demand
Lium Distributed	$1.05 /GPU/hr On-demand SXM	$0.38 /GPU/hr On-demand PCIe
GPU.ai UAE	$0.89 /GPU/hr On-demand	$0.80 /GPU/hr On-demand
Massed Compute USA	$1.35 /GPU/hr On-demand	$0.97 /GPU/hr On-demand
Packet·ai USA	$1.43 /GPU/hr On-demand	$0.92 /GPU/hr On-demand
Jarvislabs India	$0.89 /GPU/hr On-demand	--
Thunder Compute USA	$1.09 /GPU/hr On-demand	--
Runpod USA	$1.39 /GPU/hr On-demand SXM	--
Novita USA	--	$0.55 /GPU/hr On-demand
EmpirioLabs AI USA	--	$0.80 /GPU/hr On-demand
Sesterce France	--	$0.97 /GPU/hr On-demand