AMD MI325X
vs
Nvidia L40S
The MI325X is newer, with 5.3x the memory and 6.9x the bandwidth. The L40S is typically cheaper.
At a glance
Memory
5.3x more on MI325X
- MI325X
- 256 GB
- L40S
- 48 GB
Memory bandwidth
6.9x higher on MI325X
- MI325X
- 6,000 GB/s
- L40S
- 864 GB/s
Cheapest on-demand
76% cheaper on L40S
- MI325X
- $2.25 /GPU/hr
- L40S
- $0.55 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI325X | L40S | Difference |
|---|---|---|---|
| On-demand | $3.11 /GPU/hr from $2.25 | $1.64 /GPU/hr from $0.55 | 47% cheaper on L40S |
| Reserved | $1.95 /GPU/hr from $1.50 (12 mo) | $1.16 /GPU/hr from $0.61 (12 mo) | 41% cheaper on L40S |
| Spot | Sold out | $0.99 /GPU/hr from $0.74 |
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. Verify before provisioning. More on how we price.
Price history
MI325X vs L40S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI325X | L40S | 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 | 733 TFLOPS | 3.6x higher on MI325X |
| FP16 / BF16 | 1,307.4 TFLOPS | 362.1 TFLOPS | 3.6x higher on MI325X |
| INT8 | 2,614.9 TOPS | 733 TOPS | 3.6x higher on MI325X |
| FP32 | 163.4 TFLOPS | 91.6 TFLOPS | 78% 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 | 350 W | 2.9x higher on MI325X |
| Released | Q4 2024 | Q3 2023 | 14 months newer on MI325X |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI325X datasheet and L40S datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | MI325X | L40S |
|---|---|---|
Bentaus
USA
|
$2.25 /GPU/hr On-demand | -- |
Cyfuture AI
India
|
$3.06 /GPU/hr On-demand | -- |
DigitalOcean
USA
|
$3.80 /GPU/hr On-demand | -- |
TensorWave
USA
|
$2.25 /GPU/hr Custom OAM | -- |
Vultr
USA
|
$2.00 /GPU/hr Spot | -- |
Novita
USA
|
-- | $0.55 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $0.79 /GPU/hr On-demand |
Runpod
USA
|
-- | $0.79 /GPU/hr On-demand |
Packet·ai
USA
|
-- | $0.92 /GPU/hr On-demand |
Sesterce
France
|
-- | $0.97 /GPU/hr On-demand |
Massed Compute
USA
|
-- | $0.97 /GPU/hr On-demand |
Runcrate
USA
|
-- | $1.14 /GPU/hr On-demand PCIe |
UpCloud
Finland
|
-- | $1.19 /GPU/hr On-demand |
5 providers list the MI325X and 37 the L40S. Every listing is on the MI325X page and the L40S page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI325X was last updated on Sept. 14, 2026, and for Nvidia L40S on Sept. 14, 2026.