Overview

Nvidia logo Nvidia A40

The Nvidia A40 is a data center GPU on the Ampere architecture, released Q4 2020, with 48 GB GDDR6 and 696 GB/s memory bandwidth.

Mid-Range Datacenter

Nvidia logo Nvidia GB300

The Nvidia GB300 is a data center GPU on the Grace Blackwell Ultra architecture, released Q1 2025, with 288 GB HBM3e and 8,000 GB/s memory bandwidth.

High Performance Datacenter

Memory per GPU

6x more on GB300
Nvidia logo A40
48 GB GDDR6
Nvidia logo GB300
288 GB HBM3e

Memory bandwidth

11x higher on GB300
Nvidia logo A40
696 GB/s
Nvidia logo GB300
8,000 GB/s

GPU interconnect

Nvidia logo A40
PCIe only
Nvidia logo GB300
NVLink 1,800 GB/s

Peak performance (FP16)

17x higher on GB300
Nvidia logo A40
149.7 TFLOPS
Nvidia logo GB300
2,500 TFLOPS

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

FP16 per watt

3.6x higher on GB300
Nvidia logo A40
0.50 TFLOPS/W
Nvidia logo GB300
1.79 TFLOPS/W

Board power

4.7x higher on GB300
Nvidia logo A40
300 W
Nvidia logo GB300
1,400 W

Precision support

Nvidia logo A40
FP16 BF16 TF32 FP32 INT4 INT8
Nvidia logo GB300
FP4 FP6 FP8 FP16 BF16 TF32 FP32 FP64 INT8

Highlighted formats are supported by only one of the two.

Architecture

Nvidia logo A40
Ampere
Nvidia logo GB300
Grace Blackwell Ultra

Released

4 years newer on GB300
Nvidia logo A40
Q4 2020
Nvidia logo GB300
Q1 2025

Price comparison

Cheapest on-demand

41x higher on GB300
Nvidia logo A40
$0.44 / GPU / hr
Nvidia logo GB300
$18.00 / GPU / hr

Typical rate

24x higher on GB300
Nvidia logo A40
$0.74 / GPU / hr
Nvidia logo GB300
$18.00 / GPU / hr

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

Providers listing it

1 more on GB300
Nvidia logo A40
5
Nvidia logo GB300
6

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:

  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.

Similar GPUs

Other comparisons in the same class:

View all GPUs

Our data for Nvidia A40 was last updated on Aug. 31, 2026, and for Nvidia GB300 on Aug. 31, 2026.