AMD MI300X vs L40S: cloud rental cost compared

You can rent both by the hour, no purchase required. AMD MI300X from $2.99/GPU/hr across 1 provider; L40S from $0.880/GPU/hr across 2 providers. The L40S is 71% cheaper at the entry rate.

AMD MI300X
Good for training and serving frontier-scale LLMs
$2.99/hr
Lowest / GPU
$2.99/hr
Median / GPU
192 GB
VRAM
CDNA3
Architecture
L40S
Good for fine-tuning mid-size models and high-throughput inference
$0.880/hr
Lowest / GPU
$0.935/hr
Median / GPU
48 GB
VRAM
Ada Lovelace
Architecture

Specs side by side

Spec
AMD MI300X
L40S
VRAM
192 GB
48 GB
Architecture
CDNA3
Ada Lovelace
Compute capability
n/a
8.9
Precisions in hardware
FP32, FP16, BF16, FP8, INT4
FP32, FP16, BF16, FP8, INT4
Interconnect
PCIe
PCIe
Lowest $/GPU/hr
$2.99
$0.880
Median $/GPU/hr
$2.99
$0.935
Providers
1
2
Regions
1
2

Price by provider

Provider
AMD MI300X $/GPU/hr
L40S $/GPU/hr
Massed Compute
$0.880
RunPod
$0.990
Hot Aisle
$2.99

AMD MI300X vs L40S: common questions

Is the AMD MI300X or the L40S cheaper to rent?

On Aquanode's live marketplace the AMD MI300X starts at $2.99/GPU/hr (median $2.99/GPU/hr across 1 provider) and the L40S starts at $0.880/GPU/hr (median $0.935/GPU/hr across 2 providers). The L40S is the cheaper of the two at the entry rate, by 71%.

What is the difference between the AMD MI300X and the L40S?

The AMD MI300X has 192 GB of VRAM against the L40S's 48 GB; the AMD MI300X is a CDNA3 part and the L40S is Ada Lovelace; both run BF16, FP8, INT4 workloads in hardware. On price, the AMD MI300X lists from $2.99/GPU/hr and the L40S from $0.880/GPU/hr.

Which cloud providers offer the AMD MI300X and the L40S?

1 provider list the AMD MI300X (Hot Aisle) and 2 list the L40S (Massed Compute and RunPod), across 1 and 2 regions respectively. No single provider currently lists both models.

How much does 1,000 GPU-hours cost on the AMD MI300X vs the L40S?

At the lowest rates listed today, 1,000 GPU-hours costs $2,990 on the AMD MI300X and $880 on the L40S, a difference of $2,110 for the same runtime. Rates are per GPU per hour and update hourly.

How this comparison is calculated

Every price is normalized to a per-GPU hourly rate using the same pipeline as every other pricing surface on Aquanode, and only the cheapest qualifying offer per provider is shown. A dash means that provider does not currently list that GPU.

Architecture, compute capability and supported precisions come from each vendor's published datasheet for that generation, not from the marketplace feed. This page regenerates at most once per hour.

Ready when you are

Your next GPU already
has your environment on it.

Sign up in 60 seconds. Pay for the GPU minutes you actually use.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.