Two Nvidia data center GPUs, one Ada Lovelace and one Pascal: 24 GB GDDR6 against 24 GB GDDR5 and 15% more memory bandwidth on the P40.

At a glance

Updated 6 minutes ago
Memory
24 GB
GDDR6
Memory bandwidth
300 GB/s
From
$0.32 /GPU/hr
19 providers
Memory
24 GB
GDDR5
Memory bandwidth
346 GB/s
From
--

Price comparison

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

Billing L4 P40 Difference
On-demand $0.32 --
Spot $0.23 No spot listings
Reserved $0.32 No reserved listings
Median $0.90 --

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

Price history

L4 vs P40 price history

Weekly median on-demand price per GPU per hour

Last 13 months
Aggregating historical prices...

Specs comparison

Spec L4 P40 Difference
Memory
Capacity 24 GB GDDR6 24 GB GDDR5 Identical
Bandwidth 300 GB/s 346 GB/s 1.2x higher on P40
Bus width 192-bit 384-bit 2x wider on P40
Compute · dense
FP8 242 TFLOPS Not supported L4 only
FP16 / BF16 121 TFLOPS
INT8 242 TOPS 47 TOPS 5.1x higher on L4
FP32 30.3 TFLOPS 12 TFLOPS 2.5x higher on L4
Platform
Interconnect PCIe only PCIe only
Board power 72 W 250 W 3.5x higher on P40
Released Q1 2023 Q3 2016 6 years newer on L4
Precision
Supported formats FP8FP16BF16TF32FP32INT4INT8 FP16FP32INT8

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

Source: L4 datasheet and P40 datasheet.

Where to rent them

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

Provider L4 /GPU/hr P40 /GPU/hr
Vast.ai logo Vast.ai On-Demand $0.32 --
GPU.ai logo GPU.ai On-Demand $0.44 --
Runpod logo Runpod On-Demand $0.49 --
UpCloud logo UpCloud On-Demand $0.69 --
Scaleway logo Scaleway On-Demand $0.91 --
Sesterce logo Sesterce On-Demand $1.04 --
Runcrate logo Runcrate On-Demand $1.05 --
Hexabyte logo Hexabyte On-Demand $0.42 --

19 providers list the L4 and 0 the P40. Every listing is on the L4 page and the P40 page.

Similar GPUs

Other comparisons in the same class.

Our data for Nvidia L4 was last updated on Sept. 7, 2026, and for Nvidia P40 on Sept. 7, 2026.