Nvidia H100 vs Nvidia Vera Rubin

The Vera Rubin is newer, with 3.6x the memory and 5.7x the bandwidth. 6 providers list it, against 64 for the H100.

At a glance

Memory

3.6x more on Vera Rubin

H100: 80 GB

Vera Rubin: 288 GB

Memory bandwidth

5.7x higher on Vera Rubin

H100: 3.35 TB/s

Vera Rubin: 19.20 TB/s

Cheapest on-demand

Vera Rubin is not sold on demand

H100: $1.80 /GPU/hr

Vera Rubin: --

Price comparison

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

Billing	H100	Vera Rubin
On-demand	$3.99 /GPU/hr from $1.80	No on-demand listings
Reserved	$3.17 /GPU/hr from $1.53 (1 mo)	-- /GPU/hr
Spot	$2.34 /GPU/hr from $0.75	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 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

H100 vs Vera Rubin price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	H100	Vera Rubin	Difference
Memory
Capacity	80 GB HBM3 94 GB on NVL	288 GB HBM4	3.6x more on Vera Rubin
Bandwidth	3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL	19,200 GB/s	5.7x higher on Vera Rubin
Bus width	5,120-bit
Compute · dense
FP4	Not supported	35,000 TFLOPS	Vera Rubin only
FP8	1,979 TFLOPS	17,500 TFLOPS	8.8x higher on Vera Rubin
FP16 / BF16	989.5 TFLOPS	4,000 TFLOPS	4x higher on Vera Rubin
INT8	1,979 TOPS	250 TOPS	7.9x higher on H100
FP32	67 TFLOPS	130 TFLOPS	94% higher on Vera Rubin
FP64	34 TFLOPS	33 TFLOPS	Within 5%
Platform
Interconnect	NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL	NVLink 3,000 GB/s	3.3x higher on Vera Rubin
Released	Q3 2022	Q1 2026	3 years newer on Vera Rubin
Precision
Supported formats	FP8FP16BF16TF32FP32FP64INT8	FP4FP6FP8FP16BF16TF32FP32FP64INT8

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: H100 datasheet and Vera Rubin datasheet.

Where to rent them

Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.

Provider	H100	Vera Rubin
HyperAI Hong Kong	$1.80 /GPU/hr On-demand	--
Lium Distributed	$2.50 /GPU/hr On-demand SXM	--
Spheron Singapore	$2.75 /GPU/hr On-demand NVL	--
Massed Compute USA	$3.11 /GPU/hr On-demand NVL	--
Scaleway France	$3.20 /GPU/hr On-demand PCIe	--
Jarvislabs India	$3.49 /GPU/hr On-demand SXM	--
Runcrate USA	$3.58 /GPU/hr On-demand SXM	--
Oblivus USA	$3.64 /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
Hyperstack UK	--	On request Custom NVL