Overview
AMD MI325X
Highest memory capacity AMD GPU for single-chip model serving.
Nvidia L40S
Cost-effective data center GPU for AI inference and media workloads.
Memory per GPU
5.3x more on MI325X
MI325X
L40S
Memory bandwidth
6.9x higher on MI325X
MI325X
L40S
GPU interconnect
MI325X
L40S
Peak performance (FP16)
7.2x higher on MI325X
MI325X
L40S
Vendor peak figures. Sparsity and tensor-core conventions differ between vendors.
Precision support
MI325X
L40S
Highlighted formats are supported by only one of the two.
Architecture
MI325X
L40S
Released
14 months newer on MI325X
MI325X
L40S
Source: MI325X datasheet and L40S datasheet.
Price comparison
Cheapest on-demand
4.2x higher on MI325X
MI325X
L40S
Typical rate
2x higher on MI325X
MI325X
L40S
Median across providers, one vote each, so a large catalog does not outweigh a small one.
Spot floor
MI325X
L40S
Full price range
MI325X
L40S
Lowest to highest listing per GPU-hour, across on-demand, spot, reserved and custom.
Providers listing it
27 more on L40S
MI325X
L40S
Price, last 90 days
MI325X
L40S
Change in the market-wide median, which moves when providers reprice and when cheaper or more expensive listings enter the market. Withheld where too few providers price the card, its history is too short, or its weekly print swings too hard to read as a trend.
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:
- 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.
MI325X Offers
1 of 2 providers report available stock, 3 more publish no status.
L40S Offers
16 of 17 providers report available stock, 15 more publish no status.
Similar GPUs
Other comparisons in the same class:
Our data for AMD MI325X was last updated on Aug. 21, 2026, and for Nvidia L40S on Aug. 21, 2026.