Two AMD data center GPUs on the CDNA 3 architecture: 192 GB HBM3 against 256 GB HBM3e and 13% more memory bandwidth on the MI325X.
At a glance
Memory
- MI300X
- 192 GB
- MI325X
- 256 GB
1.3x more on MI325X
Memory bandwidth
- MI300X
- 5.30 TB/s
- MI325X
- 6.00 TB/s
1.1x higher on MI325X
Cheapest on-demand
- MI300X
- $2.39 /GPU/hr
- MI325X
- $2.25 /GPU/hr
6% cheaper on MI325X
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI300X | MI325X | Difference |
|---|---|---|---|
| On-demand | $2.90 /GPU/hr from $2.39 | $3.06 /GPU/hr from $2.25 | 5% cheaper on MI300X |
| Reserved | $3.39 /GPU/hr from $1.61 (12 mo) | $1.95 /GPU/hr from $1.48 (12 mo) | 42% cheaper on MI325X |
| Spot | -- /GPU/hr from $1.60 | 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 | 1.3x more on MI325X |
| Bandwidth | 5,300 GB/s | 6,000 GB/s | 1.1x 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 | 1.3x 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 listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI300X /GPU/hr | MI325X /GPU/hr |
|---|---|---|
DigitalOcean
|
On-Demand $2.59 | On-Demand $3.80 |
Cyfuture AI
|
On-Demand $2.77 | On-Demand $3.01 |
Runpod
|
On-Demand $2.39 | -- |
Hot Aisle
|
On-Demand $2.99 | -- |
Oracle Cloud
|
On-Demand $6.00 | -- |
Azure
|
On-Demand $7.86 | -- |
Cirrascale
|
Reserved (12mo) $3.12 | -- |
Crusoe
|
Reservation on request | -- |
Bentaus
|
-- | On-Demand $2.25 |
TensorWave
|
-- | Custom $2.25 |
Vultr
|
-- | Spot $2.00 |
10 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.
-
Nvidia H100
80 GB HBM3 · 37% less bandwidth than the MI300X
From $1.30 /GPU/hr Compare -
Nvidia A100
80 GB HBM2e · 63% less bandwidth than the MI300X
From $0.40 /GPU/hr Compare
-
Nvidia B200
180 GB HBM3e · 28% more bandwidth than the MI325X
From $3.75 /GPU/hr Compare
-
Nvidia H200
141 GB HBM3e · 20% less bandwidth than the MI325X
From $2.09 /GPU/hr Compare
Our data for AMD MI300X was last updated on Sept. 14, 2026, and for AMD MI325X on Sept. 14, 2026.