Nvidia A40 vs Nvidia RTX 5070

A data center GPU against a consumer card, one Ampere and one Blackwell: 48 GB GDDR6 against 12 GB GDDR7 and memory bandwidth within 5%.

At a glance

Updated 7 minutes ago

Nvidia A40

Nvidia RTX 5070

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

Billing	A40	RTX 5070	Difference
On-demand	$0.49	$0.24	2x more expensive on A40
Spot	No spot listings	$0.08
Reserved	$0.61	No reserved listings
Median	$0.77	$0.28	2.7x more expensive on A40

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	A40	RTX 5070	Difference
Memory
Capacity	48 GB GDDR6	12 GB GDDR7	4x more on A40
Bandwidth	696 GB/s	672 GB/s	Within 5%
Bus width	384-bit	192-bit	2x wider on A40
Compute · dense
FP4	Not supported	493.9 TFLOPS	RTX 5070 only
FP8	Not supported	123.5 TFLOPS	RTX 5070 only
FP16 / BF16	149.7 TFLOPS	61.7 TFLOPS	2.4x higher on A40
INT8	299.3 TOPS	246.9 TOPS	1.2x higher on A40
FP32	37.4 TFLOPS	30.9 TFLOPS	1.2x higher on A40
Platform
Interconnect	PCIe only	PCIe only
Board power	300 W	250 W	1.2x higher on A40
Released	Q4 2020	Q1 2025	4 years newer on RTX 5070
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP4FP8FP16BF16TF32FP32INT8

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.