Nvidia RTX 4070 Ti Super vs Nvidia RTX 4080

Two Nvidia consumer GPUs on the Ada Lovelace architecture: both with 16 GB GDDR6X and 7% more memory bandwidth on the RTX 4080.

At a glance

Updated 10 minutes ago

Nvidia RTX 4070 Ti Super

Nvidia RTX 4080

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

Billing	RTX 4070 Ti Super	RTX 4080	Difference
On-demand	$0.26	$0.25	5% cheaper on RTX 4080
Spot	$0.09	$0.11	18% cheaper on RTX 4070 Ti Super
Median	$0.36	$0.27	26% cheaper on RTX 4080

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 4070 Ti Super	RTX 4080	Difference
Memory
Capacity	16 GB GDDR6X	16 GB GDDR6X	Identical
Bandwidth	672 GB/s	717 GB/s	1.1x higher on RTX 4080
Bus width	256-bit	256-bit	Identical
Compute · dense
FP8	176.4 TFLOPS	194.9 TFLOPS	1.1x higher on RTX 4080
FP16 / BF16	88.2 TFLOPS	97.5 TFLOPS	1.1x higher on RTX 4080
INT8	352.8 TOPS	389.9 TOPS	1.1x higher on RTX 4080
FP32	44.1 TFLOPS	48.7 TFLOPS	1.1x higher on RTX 4080
Platform
Interconnect	PCIe only	PCIe only
Board power	285 W	320 W	1.1x higher on RTX 4080
Released	Q1 2024	Q4 2022	14 months newer on RTX 4070 Ti Super
Precision
Supported formats	FP8FP16BF16TF32FP32INT4INT8	FP8FP16BF16TF32FP32INT4INT8

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.