A10 vs T4

Both are low-cost inference GPUs. The A10 offers Ampere with 24GB, the T4 provides Turing with 16GB. Choose A10 for better performance, T4 for lowest cost.

Jump to: Specs Pricing Offers Similar GPUs

Overview

Nvidia A10

The Nvidia A10 is a data center GPU on the Ampere architecture, released Q2 2021, with 24 GB GDDR6 and 600 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 A10

A10

24 GB GDDR6

16 GB GDDR6

Memory bandwidth

2x higher on A10

A10

600 GB/s

300 GB/s

GPU interconnect

A10

PCIe only

Peak performance (FP16)

1.9x higher on A10

A10

125 TFLOPS

65 TFLOPS

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

FP16 per watt

1.1x higher on T4

A10

0.83 TFLOPS/W

0.93 TFLOPS/W

Board power

2.1x higher on A10

A10

150 W

70 W

Precision support

A10

FP16 BF16 TF32 FP32 INT4 INT8

FP16 FP32 INT4 INT8

Highlighted formats are supported by only one of the two.

Architecture

A10

Ampere

Turing

Released

3 years newer on A10

A10

Q2 2021

Q3 2018

Source: A10 datasheet and T4 datasheet.

Price comparison

Cheapest on-demand

1.6x higher on A10

A10

$0.20 / GPU / hr

$0.12 / GPU / hr

Typical rate

1.8x higher on A10

A10

$1.42 / GPU / hr

$0.81 / GPU / hr

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

Spot floor

11x higher on A10

A10

$0.60 / GPU / hr

$0.06 / GPU / hr

Providers listing it

1 more on T4

A10

Price, last 90 days

A10

Held steady

−6%

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

Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.

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.