Nvidia B300 vs Nvidia Vera Rubin

The Vera Rubin has 2.4x the bandwidth, with the same 288 GB of memory. 6 providers list it, against 40 for the B300.

At a glance

Memory

Identical

B300: 288 GB

Vera Rubin: 288 GB

Memory bandwidth

2.4x higher on Vera Rubin

B300: 8.00 TB/s

Vera Rubin: 19.20 TB/s

Cheapest on-demand

Vera Rubin is not sold on demand

B300: $5.57 /GPU/hr

Vera Rubin: --

Price comparison

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

Billing	B300	Vera Rubin
On-demand	$9.50 /GPU/hr from $5.57	No on-demand listings
Reserved	$5.75 /GPU/hr from $4.32 (60 mo)	-- /GPU/hr
Spot	$5.72 /GPU/hr from $4.08	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

B300 vs Vera Rubin price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	B300	Vera Rubin	Difference
Memory
Capacity	288 GB HBM3e	288 GB HBM4	Identical
Bandwidth	8,000 GB/s	19,200 GB/s	2.4x higher on Vera Rubin
Bus width	8,192-bit
Compute · dense
FP4	14,000 TFLOPS	35,000 TFLOPS	2.5x higher on Vera Rubin
FP8	4,500 TFLOPS	17,500 TFLOPS	3.9x higher on Vera Rubin
FP16 / BF16	2,250 TFLOPS	4,000 TFLOPS	78% higher on Vera Rubin
INT8	153.5 TOPS	250 TOPS	63% higher on Vera Rubin
FP32	75 TFLOPS	130 TFLOPS	73% higher on Vera Rubin
FP64	1.2 TFLOPS	33 TFLOPS	28x higher on Vera Rubin
Platform
Interconnect	NVLink 1,800 GB/s	NVLink 3,000 GB/s	67% higher on Vera Rubin
Released	Q1 2025	Q1 2026	10 months newer on Vera Rubin
Precision
Supported formats	FP4FP6FP8FP16BF16TF32FP32FP64INT8	FP4FP6FP8FP16BF16TF32FP32FP64INT8

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

Source: B300 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	B300	Vera Rubin
Impossible Cloud Germany	$4.49 /GPU/hr Reserved	$11.05 /GPU/hr Reserved NVL
Daytona USA	$7.10 /GPU/hr On-demand	--
Lium Distributed	$11.90 /GPU/hr On-demand SXM	--
Spheron Singapore	$12.41 /GPU/hr On-demand SXM	--
Runcrate USA	$17.02 /GPU/hr On-demand NVL	--
EmpirioLabs AI USA	$23.80 /GPU/hr On-demand	--
GPUaaS USA	$5.00 /GPU/hr Custom SXM	--
TheAI UAE	$4.50 /GPU/hr Reserved SXM	--
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