A data center GPU against a consumer card, one Pascal and one Ampere: 24 GB GDDR5 against 8 GB GDDR6X and 76% more memory bandwidth on the RTX 3070 Ti.

At a glance

Updated 27 minutes ago
Memory
24 GB
GDDR5
Memory bandwidth
346 GB/s
From
--
Memory
8 GB
GDDR6X
Memory bandwidth
608 GB/s
From
$0.10 /GPU/hr
1 provider

Price comparison

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

Billing P40 RTX 3070 Ti Difference
On-demand -- $0.10
Spot No spot listings $0.06
Median -- $0.10

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Price history

P40 vs RTX 3070 Ti price history

Weekly median on-demand price per GPU per hour

Last 13 months
Aggregating historical prices...

Specs comparison

Spec P40 RTX 3070 Ti Difference
Memory
Capacity 24 GB GDDR5 8 GB GDDR6X 3x more on P40
Bandwidth 346 GB/s 608 GB/s 1.8x higher on RTX 3070 Ti
Bus width 384-bit 256-bit 1.5x wider on P40
Compute · dense
FP16 / BF16 43.5 TFLOPS
INT8 47 TOPS 174 TOPS 3.7x higher on RTX 3070 Ti
FP32 12 TFLOPS 21.8 TFLOPS 1.8x higher on RTX 3070 Ti
Platform
Interconnect PCIe only PCIe only
Board power 250 W 290 W 1.2x higher on RTX 3070 Ti
Released Q3 2016 Q2 2021 5 years newer on RTX 3070 Ti
Precision
Supported formats FP16FP32INT8 FP16BF16TF32FP32INT4INT8

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

Source: P40 datasheet and RTX 3070 Ti datasheet.

Where to rent them

Providers listing these GPUs, those with both first, so you can switch without moving clouds.

Provider P40 /GPU/hr RTX 3070 Ti /GPU/hr
Salad logo Salad -- On-Demand $0.10

Similar GPUs

Other comparisons in the same class.

Our data for Nvidia P40 was last updated on Sept. 7, 2026, and for Nvidia RTX 3070 Ti on Sept. 7, 2026.