Nvidia RTX 3090 vs Nvidia RTX 4070 Ti Super

The RTX 3090 has 50% more memory and 39% more bandwidth, and is cheaper right now.

At a glance

Memory

50% more on RTX 3090

RTX 3090: 24 GB

RTX 4070 Ti Super: 16 GB

Memory bandwidth

39% higher on RTX 3090

RTX 3090: 936 GB/s

RTX 4070 Ti Super: 672 GB/s

Cheapest on-demand

52% cheaper on RTX 3090

RTX 3090: $0.10 /GPU/hr

RTX 4070 Ti Super: $0.21 /GPU/hr

Price comparison

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

Billing	RTX 3090	RTX 4070 Ti Super
On-demand	$0.30 /GPU/hr from $0.10	-- /GPU/hr from $0.21
Reserved	-- /GPU/hr from $0.06 (1 mo)	No reserved listings
Spot	-- /GPU/hr from $0.09	-- /GPU/hr from $0.09

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 and spot on the RTX 4070 Ti Super: 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 4070 Ti Super price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	RTX 3090	RTX 4070 Ti Super	Difference
Memory
Capacity	24 GB GDDR6X	16 GB GDDR6X	50% more on RTX 3090
Bandwidth	936 GB/s	672 GB/s	39% higher on RTX 3090
Bus width	384-bit	256-bit	50% wider on RTX 3090
Compute · dense
FP8	Not supported	176.4 TFLOPS	RTX 4070 Ti Super only
FP16 / BF16	71.2 TFLOPS	88.2 TFLOPS	24% higher on RTX 4070 Ti Super
INT8	284.7 TOPS	352.8 TOPS	24% higher on RTX 4070 Ti Super
FP32	35.6 TFLOPS	44.1 TFLOPS	24% higher on RTX 4070 Ti Super
Platform
Interconnect	NVLink 112 GB/s	PCIe only	NVLink on RTX 3090 only
Board power	350 W	285 W	23% higher on RTX 3090
Released	Q3 2020	Q1 2024	3 years newer on RTX 4070 Ti Super
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP8FP16BF16TF32FP32INT4INT8

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

Source: RTX 3090 datasheet and RTX 4070 Ti Super 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 4070 Ti Super
Theta EdgeCloud Distributed	$0.16 /GPU/hr On-demand	$0.25 /GPU/hr On-demand
Salad Distributed	$0.17 /GPU/hr On-demand	$0.21 /GPU/hr On-demand
HyperAI Hong Kong	$0.10 /GPU/hr On-demand	--
Lium Distributed	$0.28 /GPU/hr On-demand	--
GPU.ai UAE	$0.50 /GPU/hr On-demand	--
Runpod USA	$0.50 /GPU/hr On-demand	--
SwissGPU Switzerland	$0.30 /GPU/hr On-demand	--
TensorDock Distributed	$0.31 /GPU/hr On-demand	--