Nvidia RTX 3090 vs Nvidia RTX 5000 Ada

The RTX 5000 Ada is newer and has 33% more memory, while the RTX 3090 has 63% more bandwidth. The RTX 3090 is cheaper right now.

At a glance

Memory

33% more on RTX 5000 Ada

RTX 3090: 24 GB

RTX 5000 Ada: 32 GB

Memory bandwidth

63% higher on RTX 3090

RTX 3090: 936 GB/s

RTX 5000 Ada: 576 GB/s

Cheapest on-demand

77% cheaper on RTX 3090

RTX 3090: $0.10 /GPU/hr

RTX 5000 Ada: $0.43 /GPU/hr

Price comparison

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

Billing	RTX 3090	RTX 5000 Ada
On-demand	$0.20 /GPU/hr from $0.10	-- /GPU/hr from $0.43
Reserved	-- /GPU/hr from $0.06 (1 mo)	-- /GPU/hr from $0.30 (3 mo)
Spot	-- /GPU/hr from $0.07	-- /GPU/hr from $0.27

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 on-demand, reserved and spot on the RTX 5000 Ada: 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 RTX 5000 Ada price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	RTX 3090	RTX 5000 Ada	Difference
Memory
Capacity	24 GB GDDR6X	32 GB GDDR6	33% more on RTX 5000 Ada
Bandwidth	936 GB/s	576 GB/s	63% higher on RTX 3090
Bus width	384-bit	256-bit	50% wider on RTX 3090
Compute · dense
FP8	Not supported	522.2 TFLOPS	RTX 5000 Ada only
FP16 / BF16	71.2 TFLOPS	261.1 TFLOPS	3.7x higher on RTX 5000 Ada
INT8	284.7 TOPS
FP32	35.6 TFLOPS	65.3 TFLOPS	83% higher on RTX 5000 Ada
Platform
Interconnect	NVLink 112 GB/s	PCIe only	NVLink on RTX 3090 only
Board power	350 W	250 W	40% higher on RTX 3090
Released	Q3 2020	Q3 2023	3 years newer on RTX 5000 Ada
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP8FP16BF16TF32FP32INT4INT8

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

Source: RTX 3090 datasheet and RTX 5000 Ada datasheet.

Where to rent them

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

Provider	RTX 3090	RTX 5000 Ada
Vast.ai USA	$0.12 /GPU/hr On-demand	$0.43 /GPU/hr On-demand
Runpod USA	$0.22 /GPU/hr On-demand	$0.49 /GPU/hr On-demand
HyperAI Hong Kong	$0.10 /GPU/hr On-demand	--
GPU.ai UAE	$0.15 /GPU/hr On-demand	--
Salad Distributed	$0.17 /GPU/hr On-demand	--
SwissGPU Switzerland	$0.30 /GPU/hr On-demand	--
TensorDock Distributed	$0.31 /GPU/hr On-demand	--
EmpirioLabs AI USA	$0.40 /GPU/hr On-demand	--