Nvidia GTX 1070 vs Nvidia RTX 4080

Two Nvidia consumer GPUs, one Pascal and one Ada Lovelace: 8 GB GDDR5 against 16 GB GDDR6X and 2.8x the memory bandwidth on the RTX 4080.

At a glance

Updated 6 minutes ago

Nvidia GTX 1070

Nvidia RTX 4080

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

Billing	GTX 1070	RTX 4080	Difference
On-demand	$0.04	$0.17	4.3x more expensive on RTX 4080
Spot	$0.02	$0.11	5.5x more expensive on RTX 4080
Median	$0.04	$0.25	6.2x more expensive 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	GTX 1070	RTX 4080	Difference
Memory
Capacity	8 GB GDDR5	16 GB GDDR6X	2x more on RTX 4080
Bandwidth	256 GB/s	717 GB/s	2.8x higher on RTX 4080
Bus width	256-bit	256-bit	Identical
Compute · dense
FP8	Not supported	194.9 TFLOPS	RTX 4080 only
FP16 / BF16		97.5 TFLOPS
INT8	Not supported	389.9 TOPS	RTX 4080 only
FP32	6.5 TFLOPS	48.7 TFLOPS	7.5x higher on RTX 4080
Platform
Interconnect	PCIe only	PCIe only
Board power	150 W	320 W	2.1x higher on RTX 4080
Released	Q2 2016	Q4 2022	6 years newer on RTX 4080
Precision
Supported formats	FP16FP32	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.