L4 vs T4

The L4 offers 121 TFLOPS (FP16) at 72W with Ada Lovelace, while the T4 provides 65 TFLOPS at 70W with Turing. Choose L4 for higher performance, T4 for lower cost.

Jump to: Specs Pricing Offers Similar GPUs

Overview

Nvidia L4

The Nvidia L4 is a data center GPU on the Ada Lovelace architecture, released Q1 2023, with 24 GB GDDR6 and 300 GB/s memory bandwidth.

Mid-Range Datacenter

Nvidia T4

The Nvidia T4 is a data center GPU on the Turing architecture, released Q3 2018, with 16 GB GDDR6 and 300 GB/s memory bandwidth.

Mid-Range Datacenter

Memory per GPU

1.5x more on L4

24 GB GDDR6

16 GB GDDR6

Memory bandwidth

Identical

300 GB/s

GPU interconnect

PCIe only

Peak performance (FP16)

1.9x higher on L4

121 TFLOPS

65 TFLOPS

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

FP16 per watt

1.8x higher on L4

1.68 TFLOPS/W

0.93 TFLOPS/W

Board power

Within 5%

72 W

70 W

Precision support

FP8 FP16 BF16 TF32 FP32 INT4 INT8

FP16 FP32 INT4 INT8

Highlighted formats are supported by only one of the two.

Architecture

Ada Lovelace

Turing

Released

4 years newer on L4

Q1 2023

Q3 2018

Source: L4 datasheet and T4 datasheet.

Price comparison

Cheapest on-demand

2.7x higher on L4

$0.33 / GPU / hr

$0.12 / GPU / hr

Typical rate

1.1x higher on L4

$0.86 / GPU / hr

$0.81 / GPU / hr

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

Spot floor

1.9x higher on L4

$0.11 / GPU / hr

$0.06 / GPU / hr

Providers listing it

6 more on L4

Price, last 90 days

+2%

−6%

Change in the market-wide median, which moves when providers reprice and when cheaper or more expensive listings enter the market.

Heads up: Prices are estimates from published rates for common setups and vary by region and usage; verify with the provider before provisioning.

Offers and availability

How this list works

Order

Each provider appears once per GPU. We pick the one configuration that speaks for that provider, and rank on it in this order:

Availability: in stock, then waitlist, then not reported, then out of stock. A price you can act on outranks a cheaper one you cannot.
Billing type: on-demand first, then reserved, then spot, then quote-only. On-demand leads because it is the only rate you can hold without committing to anything.
Price: the lowest per-GPU hourly rate the provider lists, converted to USD.

The configuration we pick is chosen the same way, availability before billing before price. The rest of that provider's configurations are on the GPU's own page.

Ties sort alphabetically. Reserved rates are not separated by term length, so a three-year commitment can sit above a one-month one: the label beneath each price says which you are looking at. Providers who publish no rate are listed last within their group.

Transparency and funding

Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.