Nvidia RTX 3090 vs Nvidia RTX 5070 Ti

Both have about the same bandwidth. The RTX 3090 has 50% more memory and is typically cheaper.

At a glance

Memory

50% more on RTX 3090

RTX 3090: 24 GB

RTX 5070 Ti: 16 GB

Memory bandwidth

Within 5%

RTX 3090: 936 GB/s

RTX 5070 Ti: 896 GB/s

Cheapest on-demand

38% cheaper on RTX 3090

RTX 3090: $0.10 /GPU/hr

RTX 5070 Ti: $0.16 /GPU/hr

Price comparison

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

Billing	RTX 3090	RTX 5070 Ti	Difference
On-demand	$0.20 /GPU/hr from $0.10	$0.23 /GPU/hr from $0.16	10% cheaper on RTX 3090
Reserved	-- /GPU/hr from $0.06 (1 mo)	-- /GPU/hr from $0.19 (6 mo)
Spot	-- /GPU/hr from $0.08	-- /GPU/hr from $0.10

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 reserved and spot on the RTX 5070 Ti: 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 5070 Ti price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	RTX 3090	RTX 5070 Ti	Difference
Memory
Capacity	24 GB GDDR6X	16 GB GDDR7	50% more on RTX 3090
Bandwidth	936 GB/s	896 GB/s	Within 5%
Bus width	384-bit	256-bit	50% wider on RTX 3090
Compute · dense
FP4	Not supported	703 TFLOPS	RTX 5070 Ti only
FP8	Not supported	175.8 TFLOPS	RTX 5070 Ti only
FP16 / BF16	71.2 TFLOPS	87.9 TFLOPS	23% higher on RTX 5070 Ti
INT8	284.7 TOPS	351.5 TOPS	23% higher on RTX 5070 Ti
FP32	35.6 TFLOPS	43.9 TFLOPS	23% higher on RTX 5070 Ti
Platform
Interconnect	NVLink 112 GB/s	PCIe only	NVLink on RTX 3090 only
Board power	350 W	300 W	17% higher on RTX 3090
Released	Q3 2020	Q1 2025	4 years newer on RTX 5070 Ti
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP4FP8FP16BF16TF32FP32INT8

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

Source: RTX 3090 datasheet and RTX 5070 Ti 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 5070 Ti
Vast.ai USA	$0.12 /GPU/hr On-demand	$0.16 /GPU/hr On-demand
Salad Distributed	$0.17 /GPU/hr On-demand	$0.23 /GPU/hr On-demand
HyperAI Hong Kong	$0.10 /GPU/hr On-demand	--
GPU.ai UAE	$0.15 /GPU/hr On-demand	--
Runpod USA	$0.22 /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	--
Theta EdgeCloud Distributed	--	$0.31 /GPU/hr On-demand