MI325X vs H200

The MI325X features 256GB in ROCm, while the H200 provides 141GB in CUDA. Choose MI325X for larger memory, H200 for CUDA compatibility.

Overview

AMD logo AMD MI325X

The AMD MI325X is a data center GPU on the CDNA3 architecture, released Q4 2024, with 256 GB HBM3e and 6,000 GB/s memory bandwidth.

High Performance Datacenter

Nvidia logo Nvidia H200

The Nvidia H200 is a data center GPU on the Hopper architecture, released Q4 2023, with 141 GB HBM3e and 4,800 GB/s memory bandwidth.

High Performance Datacenter

Memory per GPU

1.8x more on MI325X
AMD logo MI325X
256 GB HBM3e
Nvidia logo H200
141 GB HBM3e

Memory bandwidth

1.2x higher on MI325X
AMD logo MI325X
6,000 GB/s
Nvidia logo H200
4,800 GB/s

GPU interconnect

Within 5%
AMD logo MI325X
Infinity Fabric 896 GB/s
Nvidia logo H200
NVLink 900 GB/s

Peak performance (FP8)

1.3x higher on MI325X
AMD logo MI325X
2,614.9 TFLOPS
Nvidia logo H200
1,979 TFLOPS

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

FP8 per watt

1.1x higher on H200
AMD logo MI325X
2.61 TFLOPS/W
Nvidia logo H200
2.83 TFLOPS/W

Board power

1.4x higher on MI325X
AMD logo MI325X
1,000 W
Nvidia logo H200
700 W

Precision support

AMD logo MI325X
FP8 FP16 BF16 TF32 FP32 FP64 INT8
Nvidia logo H200
FP8 FP16 BF16 TF32 FP32 FP64 INT8

Highlighted formats are supported by only one of the two.

Architecture

AMD logo MI325X
CDNA3
Nvidia logo H200
Hopper

Released

11 months newer on MI325X
AMD logo MI325X
Q4 2024
Nvidia logo H200
Q4 2023

Price comparison

Cheapest on-demand

1.1x higher on MI325X
AMD logo MI325X
$2.25 / GPU / hr
Nvidia logo H200
$1.99 / GPU / hr

Typical rate

1.4x higher on H200
AMD logo MI325X
$3.09 / GPU / hr
Nvidia logo H200
$4.40 / GPU / hr

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

Spot floor

AMD logo MI325X
No spot listings
Nvidia logo H200
$0.43 / GPU / hr

Providers listing it

35 more on H200
AMD logo MI325X
5
Nvidia logo H200
40

Price, last 90 days

AMD logo MI325X
Not enough history yet
Nvidia logo H200
+3%

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:

  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 AMD MI325X was last updated on Aug. 31, 2026, and for Nvidia H200 on Aug. 31, 2026.