Nvidia RTX 3090 Ti vs Nvidia RTX 5090

Two Nvidia consumer GPUs, one Ampere and one Blackwell: 24 GB GDDR6X against 32 GB GDDR7 and 78% more memory bandwidth on the RTX 5090.

At a glance

Updated 8 minutes ago

Nvidia RTX 3090 Ti

Nvidia RTX 5090

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing	RTX 3090 Ti	RTX 5090	Difference
On-demand	$0.28	$0.35	20% cheaper on RTX 3090 Ti
Spot	$0.10	$0.25	2.5x more expensive on RTX 5090
Reserved	No reserved listings	$0.21
Median	$0.28	$0.69	2.5x more expensive on RTX 5090

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Spec	RTX 3090 Ti	RTX 5090	Difference
Memory
Capacity	24 GB GDDR6X	32 GB GDDR7	1.3x more on RTX 5090
Bandwidth	1,008 GB/s	1,792 GB/s	1.8x higher on RTX 5090
Bus width	384-bit	512-bit	1.3x wider on RTX 5090
Compute · dense
FP4	Not supported	1,676 TFLOPS	RTX 5090 only
FP8	Not supported	419 TFLOPS	RTX 5090 only
FP16 / BF16	80 TFLOPS	209.5 TFLOPS	2.6x higher on RTX 5090
INT8	320 TOPS	838 TOPS	2.6x higher on RTX 5090
FP32	40 TFLOPS	104.8 TFLOPS	2.6x higher on RTX 5090
Platform
Interconnect	PCIe only	PCIe only
Board power	450 W	575 W	1.3x higher on RTX 5090
Released	Q1 2022	Q1 2025	3 years newer on RTX 5090
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP4FP8FP16BF16TF32FP32INT8

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

Providers listing these GPUs, those with both first, so you can switch without moving clouds.