Nvidia RTX 3090 vs Nvidia Vera Rubin

The Vera Rubin is newer, with 12x the memory and 21x the bandwidth.

At a glance

Memory

12x more on Vera Rubin

RTX 3090: 24 GB

Vera Rubin: 288 GB

Memory bandwidth

21x higher on Vera Rubin

RTX 3090: 936 GB/s

Vera Rubin: 19,200 GB/s

Cheapest on-demand

Vera Rubin is not sold on demand

RTX 3090: $0.10 /GPU/hr

Vera Rubin: --

Price comparison

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

Billing	RTX 3090	Vera Rubin
On-demand	$0.22 /GPU/hr from $0.10	No on-demand listings
Reserved	-- /GPU/hr from $0.06 (1 mo)	-- /GPU/hr
Spot	-- /GPU/hr from $0.09	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 and spot on the RTX 3090 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

RTX 3090 vs Vera Rubin price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	RTX 3090	Vera Rubin	Difference
Memory
Capacity	24 GB GDDR6X	288 GB HBM4	12x more on Vera Rubin
Bandwidth	936 GB/s	19,200 GB/s	21x higher on Vera Rubin
Bus width	384-bit
Compute · dense
FP4	Not supported	35,000 TFLOPS	Vera Rubin only
FP8	Not supported	17,500 TFLOPS	Vera Rubin only
FP16 / BF16	71.2 TFLOPS	4,000 TFLOPS	56x higher on Vera Rubin
INT8	284.7 TOPS	250 TOPS	14% higher on RTX 3090
FP32	35.6 TFLOPS	130 TFLOPS	3.7x higher on Vera Rubin
FP64	Not supported	33 TFLOPS	Vera Rubin only
Platform
Interconnect	NVLink 112 GB/s	NVLink 3,000 GB/s	27x higher on Vera Rubin
Released	Q3 2020	Q1 2026	5 years newer on Vera Rubin
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP4FP6FP8FP16BF16TF32FP32FP64INT8

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

Source: RTX 3090 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	RTX 3090	Vera Rubin
HyperAI Hong Kong	$0.10 /GPU/hr On-demand	--
Theta EdgeCloud Distributed	$0.16 /GPU/hr On-demand	--
GPU.ai UAE	$0.16 /GPU/hr On-demand	--
Lium Distributed	$0.18 /GPU/hr On-demand	--
OpenRelay USA	$0.18 /GPU/hr On-demand	--
Salad Distributed	$0.20 /GPU/hr On-demand	--
TensorDock Distributed	$0.31 /GPU/hr On-demand	--
SwissGPU Switzerland	$0.43 /GPU/hr On-demand	--
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