The MI325X has 33% more memory and 13% more bandwidth. The two typically cost about the same.
At a glance
Memory
33% more on MI325X
- MI300X
- 192 GB
- MI325X
- 256 GB
Memory bandwidth
13% higher on MI325X
- MI300X
- 5.30 TB/s
- MI325X
- 6.00 TB/s
Cheapest on-demand
13% cheaper on MI325X
- MI300X
- $2.59 /GPU/hr
- MI325X
- $2.25 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI300X | MI325X | Difference |
|---|---|---|---|
| On-demand | $2.99 /GPU/hr from $2.59 | $3.03 /GPU/hr from $2.25 | Within 5% |
| Reserved | $2.79 /GPU/hr from $1.59 (12 mo) | $1.95 /GPU/hr from $1.46 (12 mo) | 30% cheaper on MI325X |
| Spot | -- /GPU/hr from $1.76 | Sold out |
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 MI300X: 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
MI300X vs MI325X price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI300X | MI325X | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3 | 256 GB HBM3e | 33% more on MI325X |
| Bandwidth | 5,300 GB/s | 6,000 GB/s | 13% higher on MI325X |
| Bus width | 8,192-bit | 8,192-bit | Identical |
| Compute · dense | |||
| FP8 | 2,614.9 TFLOPS | 2,614.9 TFLOPS | Identical |
| FP16 / BF16 | 1,307.4 TFLOPS | 1,307.4 TFLOPS | Identical |
| INT8 | 2,614.9 TOPS | 2,614.9 TOPS | Identical |
| FP32 | 163.4 TFLOPS | 163.4 TFLOPS | Identical |
| FP64 | 81.7 TFLOPS | 81.7 TFLOPS | Identical |
| Platform | |||
| Interconnect | Infinity Fabric 896 GB/s | Infinity Fabric 896 GB/s | Identical |
| Board power | 750 W | 1,000 W | 33% higher on MI325X |
| Released | Q4 2023 | Q4 2024 | 10 months newer on MI325X |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI300X datasheet and MI325X datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | MI300X | MI325X |
|---|---|---|
Cyfuture AI
India
|
$2.75 /GPU/hr On-demand | $2.98 /GPU/hr On-demand |
DigitalOcean
USA
|
$2.59 /GPU/hr On-demand | $3.80 /GPU/hr On-demand |
Hot Aisle
USA
|
$2.99 /GPU/hr On-demand | -- |
Denvr
Canada
|
On request Custom | -- |
Oracle Cloud
USA
|
$6.00 /GPU/hr On-demand | -- |
Azure
USA
|
$7.86 /GPU/hr On-demand | -- |
Cirrascale
USA
|
$3.12 /GPU/hr Reserved | -- |
Crusoe
USA
|
On request Reserved | -- |
Bentaus
USA
|
-- | $2.25 /GPU/hr On-demand |
TensorWave
USA
|
-- | $2.25 /GPU/hr Custom OAM |
Vultr
USA
|
-- | $2.00 /GPU/hr Spot |
11 providers list the MI300X and 5 the MI325X. Every listing is on the MI300X page and the MI325X page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI300X was last updated on Sept. 14, 2026, and for AMD MI325X on Sept. 14, 2026.