Nvidia L4 vs Nvidia L40S

The L40S has 2x the memory and 2.9x the bandwidth. The L4 is typically cheaper.

At a glance

Memory

2x more on L40S

L4: 24 GB

L40S: 48 GB

Memory bandwidth

2.9x higher on L40S

L4: 300 GB/s

L40S: 864 GB/s

Cheapest on-demand

50% cheaper on L4

L4: $0.27 /GPU/hr

L40S: $0.54 /GPU/hr

Price comparison

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

Billing	L4	L40S	Difference
On-demand	$0.86 /GPU/hr from $0.27	$1.57 /GPU/hr from $0.54	45% cheaper on L4
Reserved	$0.51 /GPU/hr from $0.32 (36 mo)	$1.04 /GPU/hr from $0.49 (6 mo)	51% cheaper on L4
Spot	$0.29 /GPU/hr from $0.13	$0.90 /GPU/hr from $0.34	68% cheaper on L4

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

L4 vs L40S price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	L4	L40S	Difference
Memory
Capacity	24 GB GDDR6	48 GB GDDR6	2x more on L40S
Bandwidth	300 GB/s	864 GB/s	2.9x higher on L40S
Bus width	192-bit	384-bit	2x wider on L40S
Compute · dense
FP8	242 TFLOPS	733 TFLOPS	3x higher on L40S
FP16 / BF16	121 TFLOPS	362.1 TFLOPS	3x higher on L40S
INT8	242 TOPS	733 TOPS	3x higher on L40S
FP32	30.3 TFLOPS	91.6 TFLOPS	3x higher on L40S
Platform
Interconnect	PCIe only	PCIe only
Board power	72 W	350 W	4.9x higher on L40S
Released	Q1 2023	Q3 2023
Precision
Supported formats	FP8FP16BF16TF32FP32INT4INT8	FP8FP16BF16TF32FP32INT4INT8

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

Source: L4 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	L4	L40S
Vast.ai USA	$0.27 /GPU/hr On-demand	$0.54 /GPU/hr On-demand
GPU.ai UAE	$0.27 /GPU/hr On-demand	$0.60 /GPU/hr On-demand
Sesterce France	$1.04 /GPU/hr On-demand	$0.97 /GPU/hr On-demand
Jarvislabs India	$0.44 /GPU/hr On-demand	--
Scaleway France	$0.88 /GPU/hr On-demand	--
Hexabyte Sweden	$0.40 /GPU/hr On-demand	--
Leaseweb Netherlands	$0.43 /GPU/hr On-demand	--
Koyeb France	$0.70 /GPU/hr On-demand	--
Novita USA	--	$0.55 /GPU/hr On-demand
Runpod USA	--	$0.79 /GPU/hr On-demand
Packet·ai USA	--	$0.92 /GPU/hr On-demand
Massed Compute USA	--	$0.97 /GPU/hr On-demand
Runcrate USA	--	$1.14 /GPU/hr On-demand PCIe