AMD MI325X
vs
Nvidia L40
Two data center GPUs, one CDNA 3 and one Ada Lovelace: 256 GB HBM3e against 48 GB GDDR6, 6.9x the memory bandwidth on the MI325X, and Infinity Fabric 896 GB/s on the MI325X where the L40 is PCIe only.
At a glance
Memory
- MI325X
- 256 GB
- L40
- 48 GB
5.3x more on MI325X
Memory bandwidth
- MI325X
- 6,000 GB/s
- L40
- 864 GB/s
6.9x higher on MI325X
Cheapest on-demand
- MI325X
- $2.25 /GPU/hr
- L40
- $0.79 /GPU/hr
2.8x more expensive on MI325X
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI325X | L40 | Difference |
|---|---|---|---|
| On-demand | $3.07 /GPU/hr from $2.25 | $1.05 /GPU/hr from $0.79 | 2.9x more expensive on MI325X |
| Reserved | $1.95 /GPU/hr from $1.48 (12 mo) | -- /GPU/hr from $0.70 | |
| Spot | Sold out | $0.80 /GPU/hr from $0.78 |
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. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for reserved on the L40: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
MI325X vs L40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI325X | L40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 256 GB HBM3e | 48 GB GDDR6 | 5.3x more on MI325X |
| Bandwidth | 6,000 GB/s | 864 GB/s | 6.9x higher on MI325X |
| Bus width | 8,192-bit | 384-bit | 21x wider on MI325X |
| Compute · dense | |||
| FP8 | 2,614.9 TFLOPS | 362 TFLOPS | 7.2x higher on MI325X |
| FP16 / BF16 | 1,307.4 TFLOPS | 181.1 TFLOPS | 7.2x higher on MI325X |
| INT8 | 2,614.9 TOPS | 362 TOPS | 7.2x higher on MI325X |
| FP32 | 163.4 TFLOPS | 90.5 TFLOPS | 1.8x higher on MI325X |
| FP64 | 81.7 TFLOPS | Not supported | MI325X only |
| Platform | |||
| Interconnect | Infinity Fabric 896 GB/s | PCIe only | Infinity Fabric on MI325X only |
| Board power | 1,000 W | 300 W | 3.3x higher on MI325X |
| Released | Q4 2024 | Q4 2022 | 2 years newer on MI325X |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI325X datasheet and L40 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI325X /GPU/hr | L40 /GPU/hr |
|---|---|---|
Bentaus
|
On-Demand $2.25 | -- |
Cyfuture AI
|
On-Demand $3.02 | -- |
DigitalOcean
|
On-Demand $3.80 | -- |
TensorWave
|
Custom $2.25 | -- |
Vultr
|
Spot $2.00 | -- |
Thunder Compute
|
-- | On-Demand $0.79 |
Runcrate
|
-- | On-Demand $0.97 |
Oblivus
|
-- | On-Demand $1.05 |
EmpirioLabs AI
|
-- | On-Demand $1.50 |
Spheron
|
-- | Spot $0.88 |
Hyperstack
|
-- | On-Demand $1.00 |
TensorDock
|
-- | On-Demand $1.06 |
CoreWeave
|
-- | On-Demand $1.25 |
5 providers list the MI325X and 12 the L40. Every listing is on the MI325X page and the L40 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
From $1.45 /GPU/hr Compare -
Nvidia B200
From $3.75 /GPU/hr Compare -
Nvidia H200
From $2.09 /GPU/hr Compare -
Nvidia A100
From $0.54 /GPU/hr Compare -
Nvidia L40S
From $0.55 /GPU/hr Compare
Our data for AMD MI325X was last updated on Sept. 7, 2026, and for Nvidia L40 on Sept. 7, 2026.