Nvidia GB300 vs Nvidia RTX 3090

The GB300 is newer, with 12x the memory and 8.5x the bandwidth. The RTX 3090 is cheaper right now.

At a glance

Memory

12x more on GB300

GB300: 288 GB

RTX 3090: 24 GB

Memory bandwidth

8.5x higher on GB300

GB300: 8,000 GB/s

RTX 3090: 936 GB/s

Cheapest on-demand

99% cheaper on RTX 3090

GB300: $18.00 /GPU/hr

RTX 3090: $0.10 /GPU/hr

Price comparison

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

Billing	GB300	RTX 3090
On-demand	-- /GPU/hr from $18.00	$0.20 /GPU/hr from $0.10
Reserved	On request	-- /GPU/hr from $0.06 (1 mo)
Spot	Sold out	-- /GPU/hr from $0.08

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 on-demand on the GB300 and reserved and spot on the RTX 3090: 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

GB300 vs RTX 3090 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	GB300	RTX 3090	Difference
Memory
Capacity	288 GB HBM3e	24 GB GDDR6X	12x more on GB300
Bandwidth	8,000 GB/s	936 GB/s	8.5x higher on GB300
Bus width	8,192-bit	384-bit	21x wider on GB300
Compute · dense
FP4	15,000 TFLOPS	Not supported	GB300 only
FP8	5,000 TFLOPS	Not supported	GB300 only
FP16 / BF16	2,500 TFLOPS	71.2 TFLOPS	35x higher on GB300
INT8	165 TOPS	284.7 TOPS	73% higher on RTX 3090
FP32	80 TFLOPS	35.6 TFLOPS	2.2x higher on GB300
FP64	1.3 TFLOPS	Not supported	GB300 only
Platform
Interconnect	NVLink 1,800 GB/s	NVLink 112 GB/s	16x higher on GB300
Board power	1,400 W	350 W	4x higher on GB300
Released	Q1 2025	Q3 2020	4 years newer on GB300
Precision
Supported formats	FP4FP6FP8FP16BF16TF32FP32FP64INT8	FP16BF16TF32FP32INT4INT8

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

Source: GB300 datasheet and RTX 3090 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	GB300	RTX 3090
Oracle Cloud USA	$18.00 /GPU/hr On-demand NVL	--
AWS USA	On request Reserved	--
CoreWeave USA	On request Custom NVL	--
Gcore Luxembourg	On request Custom NVL	--
Nebius Netherlands	On request Custom NVL	--
Together AI USA	On request Custom NVL	--
Verda Finland	$9.15 /GPU/hr On-demand SXM	--
HyperAI Hong Kong	--	$0.10 /GPU/hr On-demand
Theta EdgeCloud Distributed	--	$0.13 /GPU/hr On-demand
Vast.ai USA	--	$0.15 /GPU/hr On-demand
Lium Distributed	--	$0.16 /GPU/hr On-demand
GPU.ai UAE	--	$0.17 /GPU/hr On-demand
Salad Distributed	--	$0.17 /GPU/hr On-demand
EmpirioLabs AI USA	--	$0.35 /GPU/hr On-demand
SwissGPU Switzerland	--	$0.30 /GPU/hr On-demand