AMD MI325X
vs
Nvidia L4
The MI325X is newer, with 11x the memory and 20x the bandwidth. The L4 is typically cheaper.
At a glance
Memory
11x more on MI325X
- MI325X
- 256 GB
- L4
- 24 GB
Memory bandwidth
20x higher on MI325X
- MI325X
- 6,000 GB/s
- L4
- 300 GB/s
Cheapest on-demand
86% cheaper on L4
- MI325X
- $2.25 /GPU/hr
- L4
- $0.33 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI325X | L4 | Difference |
|---|---|---|---|
| On-demand | $3.09 /GPU/hr from $2.25 | $0.81 /GPU/hr from $0.33 | 74% cheaper on L4 |
| Reserved | $1.95 /GPU/hr from $1.49 (12 mo) | $0.52 /GPU/hr from $0.32 (36 mo) | 73% cheaper on L4 |
| Spot | Sold out | -- /GPU/hr from $0.29 |
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 spot on the L4: 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 L4 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI325X | L4 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 256 GB HBM3e | 24 GB GDDR6 | 11x more on MI325X |
| Bandwidth | 6,000 GB/s | 300 GB/s | 20x higher on MI325X |
| Bus width | 8,192-bit | 192-bit | 43x wider on MI325X |
| Compute · dense | |||
| FP8 | 2,614.9 TFLOPS | 242 TFLOPS | 11x higher on MI325X |
| FP16 / BF16 | 1,307.4 TFLOPS | 121 TFLOPS | 11x higher on MI325X |
| INT8 | 2,614.9 TOPS | 242 TOPS | 11x higher on MI325X |
| FP32 | 163.4 TFLOPS | 30.3 TFLOPS | 5.4x 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 | 72 W | 14x higher on MI325X |
| Released | Q4 2024 | Q1 2023 | 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 L4 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 | L4 |
|---|---|---|
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 | -- |
Theta EdgeCloud
Distributed
|
-- | $0.33 /GPU/hr On-demand |
Jarvislabs
India
|
-- | $0.44 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $0.59 /GPU/hr On-demand |
Runpod
USA
|
-- | $0.59 /GPU/hr On-demand |
Runcrate
USA
|
-- | $1.23 /GPU/hr On-demand PCIe |
Hexabyte
Sweden
|
-- | $0.40 /GPU/hr On-demand |
Leaseweb
Netherlands
|
-- | $0.43 /GPU/hr On-demand |
Koyeb
France
|
-- | $0.70 /GPU/hr On-demand |
5 providers list the MI325X and 21 the L4. Every listing is on the MI325X page and the L4 page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI325X was last updated on Sept. 14, 2026, and for Nvidia L4 on Sept. 14, 2026.