Nvidia logo

A10G vs T4G

Both are AWS-optimized. The A10G offers Ampere with 24GB, the T4G has Turing with 16GB on Graviton. Choose A10G for performance, T4G for lowest cost.

Overview

Nvidia logo Nvidia A10G

AWS-optimized GPU for inference, rendering, and video transcoding.

Mid-Range Datacenter

Nvidia logo Nvidia T4G

T4 variant optimized for AWS Graviton ARM-based instances.

Mid-Range Datacenter

Memory per GPU

1.5x more on A10G
Nvidia logo A10G
24 GB GDDR6
Nvidia logo T4G
16 GB GDDR6

Memory bandwidth

1.9x higher on A10G
Nvidia logo A10G
600 GB/s
Nvidia logo T4G
320 GB/s

GPU interconnect

Nvidia logo A10G
PCIe only
Nvidia logo T4G
PCIe only

Precision support

Nvidia logo A10G
FP16 BF16 TF32 FP32 INT4 INT8
Nvidia logo T4G
FP16 FP32 INT4 INT8

Highlighted formats are supported by only one of the two.

Architecture

Nvidia logo A10G
Ampere
Nvidia logo T4G
Turing

Released

7 months newer on A10G
Nvidia logo A10G
Q2 2021
Nvidia logo T4G
Q3 2020

Price comparison

Cheapest on-demand

2.4x higher on A10G
Nvidia logo A10G
$1.01 / GPU / hr
Nvidia logo T4G
$0.42 / GPU / hr

Typical rate

1.7x higher on A10G
Nvidia logo A10G
$1.90 / GPU / hr
Nvidia logo T4G
$1.10 / GPU / hr

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

Full price range

Nvidia logo A10G
$0.43 - $4.10 / GPU / hr
Nvidia logo T4G
$0.23 - $1.37 / GPU / hr

Lowest to highest listing per GPU-hour, across on-demand, spot, reserved and custom.

Providers listing it

1 more on A10G
Nvidia logo A10G
2
Nvidia logo T4G
1

Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs 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:

  1. Availability: in stock, then waitlist, then not reported, then out of stock. A price you can act on outranks a cheaper one you cannot.
  2. 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.
  3. 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.

Nvidia A10G logo A10G Offers

1 of 1 providers report available stock, 1 more publish no status.

Nvidia T4G logo T4G Offers

1 of 1 providers report available stock.

Similar GPUs

Other comparisons in the same class:

View all GPUs

Our data for Nvidia A10G was last updated on Aug. 21, 2026, and for Nvidia T4G on Aug. 21, 2026.