Nvidia L40 vs Nvidia Vera Rubin

The Vera Rubin is newer, with 6x the memory and 22x the bandwidth.

At a glance

Memory

6x more on Vera Rubin

L40: 48 GB

Vera Rubin: 288 GB

Memory bandwidth

22x higher on Vera Rubin

L40: 864 GB/s

Vera Rubin: 19,200 GB/s

Cheapest on-demand

Vera Rubin is not sold on demand

L40: $0.33 /GPU/hr

Vera Rubin: --

Price comparison

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

Billing	L40	Vera Rubin
On-demand	$1.00 /GPU/hr from $0.33	No on-demand listings
Reserved	-- /GPU/hr from $0.70	-- /GPU/hr
Spot	$0.79 /GPU/hr from $0.78	No spot listings

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. No median for reserved on the L40 and reserved on the Vera Rubin: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.

Price history

L40 vs Vera Rubin price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	L40	Vera Rubin	Difference
Memory
Capacity	48 GB GDDR6	288 GB HBM4	6x more on Vera Rubin
Bandwidth	864 GB/s	19,200 GB/s	22x higher on Vera Rubin
Bus width	384-bit
Compute · dense
FP4	Not supported	35,000 TFLOPS	Vera Rubin only
FP8	362 TFLOPS	17,500 TFLOPS	48x higher on Vera Rubin
FP16 / BF16	181.1 TFLOPS	4,000 TFLOPS	22x higher on Vera Rubin
INT8	362 TOPS	250 TOPS	45% higher on L40
FP32	90.5 TFLOPS	130 TFLOPS	44% higher on Vera Rubin
FP64	Not supported	33 TFLOPS	Vera Rubin only
Platform
Interconnect	PCIe only	NVLink 3,000 GB/s	NVLink on Vera Rubin only
Released	Q4 2022	Q1 2026	3 years newer on Vera Rubin
Precision
Supported formats	FP8FP16BF16TF32FP32INT4INT8	FP4FP6FP8FP16BF16TF32FP32FP64INT8

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

Source: L40 datasheet and Vera Rubin datasheet.

Where to rent them

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

Provider	L40	Vera Rubin
Hyperstack UK	$1.00 /GPU/hr On-demand	On request Custom NVL
Lium Distributed	$0.33 /GPU/hr On-demand PCIe	--
Runcrate USA	$0.48 /GPU/hr On-demand PCIe	--
EmpirioLabs AI USA	$0.70 /GPU/hr On-demand	--
GPU.ai UAE	$0.86 /GPU/hr On-demand	--
Massed Compute USA	$0.86 /GPU/hr On-demand	--
Sesterce France	$0.97 /GPU/hr On-demand	--
Oblivus USA	$1.05 /GPU/hr On-demand PCIe	--
Impossible Cloud Germany	--	$11.05 /GPU/hr Reserved NVL
CUDO UK	--	On request Custom
CambridgeNexus USA	--	On request Custom NVL
Civo UK	--	On request Custom NVL
Crusoe USA	--	On request Custom NVL