Nvidia RTX 4090 vs Nvidia RTX 5090

The RTX 5090 is newer, with 33% more memory and 77% more bandwidth. The RTX 4090 is typically cheaper.

At a glance

Memory

33% more on RTX 5090

RTX 4090: 24 GB

RTX 5090: 32 GB

Memory bandwidth

77% higher on RTX 5090

RTX 4090: 1.01 TB/s

RTX 5090: 1.79 TB/s

Cheapest on-demand

6% cheaper on RTX 4090

RTX 4090: $0.33 /GPU/hr

RTX 5090: $0.35 /GPU/hr

Price comparison

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

Billing	RTX 4090	RTX 5090	Difference
On-demand	$0.44 /GPU/hr from $0.33	$0.69 /GPU/hr from $0.35	36% cheaper on RTX 4090
Reserved	$0.52 /GPU/hr from $0.25 (36 mo)	$0.59 /GPU/hr from $0.21 (1 mo)	13% cheaper on RTX 4090
Spot	$0.34 /GPU/hr from $0.16	$0.57 /GPU/hr from $0.15	41% cheaper on RTX 4090

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. Verify before provisioning. More on how we price.

Price history

RTX 4090 vs RTX 5090 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	RTX 4090	RTX 5090	Difference
Memory
Capacity	24 GB GDDR6X	32 GB GDDR7	33% more on RTX 5090
Bandwidth	1,010 GB/s	1,792 GB/s	77% higher on RTX 5090
Bus width	384-bit	512-bit	33% wider on RTX 5090
Compute · dense
FP4	Not supported	1,676 TFLOPS	RTX 5090 only
FP8	330.3 TFLOPS	419 TFLOPS	27% higher on RTX 5090
FP16 / BF16	165.2 TFLOPS	209.5 TFLOPS	27% higher on RTX 5090
INT8	660.6 TOPS	838 TOPS	27% higher on RTX 5090
FP32	82.6 TFLOPS	104.8 TFLOPS	27% higher on RTX 5090
Platform
Interconnect	PCIe only	PCIe only
Board power	450 W	575 W	28% higher on RTX 5090
Released	Q4 2022	Q1 2025	2 years newer on RTX 5090
Precision
Supported formats	FP8FP16BF16TF32FP32INT4INT8	FP4FP8FP16BF16TF32FP32INT8

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

Source: RTX 4090 datasheet and RTX 5090 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 4090	RTX 5090
Runpod USA	$0.34 /GPU/hr On-demand	$0.69 /GPU/hr On-demand
Vast.ai USA	$0.36 /GPU/hr On-demand	$0.44 /GPU/hr On-demand
GPU.ai UAE	$0.38 /GPU/hr On-demand	$0.45 /GPU/hr On-demand
Lium Distributed	$0.45 /GPU/hr On-demand	$0.55 /GPU/hr On-demand
Packet·ai USA	$0.39 /GPU/hr On-demand	--
EmpirioLabs AI USA	$0.90 /GPU/hr On-demand	--
Daytona USA	$0.99 /GPU/hr On-demand	--
GPUaaS USA	$0.50 /GPU/hr Custom	--
HyperAI Hong Kong	--	$0.35 /GPU/hr On-demand
GPUhub Singapore	--	$0.46 /GPU/hr On-demand
Nova Cloud Canada	--	$0.66 /GPU/hr On-demand PCIe
Sesterce France	--	$0.71 /GPU/hr On-demand