AMD MI325X
vs
Nvidia A100
The MI325X is newer, with 3.2x the memory and 3.1x the bandwidth. The A100 is typically cheaper.
At a glance
Memory
3.2x more on MI325X
- MI325X
- 256 GB
- A100
- 80 GB
Memory bandwidth
3.1x higher on MI325X
- MI325X
- 6.00 TB/s
- A100
- 1.94 TB/s
Cheapest on-demand
60% cheaper on A100
- MI325X
- $2.25 /GPU/hr
- A100
- $0.89 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI325X | A100 | Difference |
|---|---|---|---|
| On-demand | $3.09 /GPU/hr from $2.25 | $1.88 /GPU/hr from $0.89 | 39% cheaper on A100 |
| Reserved | $1.95 /GPU/hr from $1.49 (12 mo) | $1.67 /GPU/hr from $0.66 (24 mo) | 14% cheaper on A100 |
| Spot | Sold out | $1.19 /GPU/hr from $0.68 |
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 A100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI325X | A100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 256 GB HBM3e | 80 GB HBM2e 40 GB on SXM, PCIe | 3.2x more on MI325X |
| Bandwidth | 6,000 GB/s | 1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe | 3.1x higher on MI325X |
| Bus width | 8,192-bit | 5,120-bit | 60% wider on MI325X |
| Compute · dense | |||
| FP8 | 2,614.9 TFLOPS | Not supported | MI325X only |
| FP16 / BF16 | 1,307.4 TFLOPS | 312 TFLOPS | 4.2x higher on MI325X |
| INT8 | 2,614.9 TOPS | 624 TOPS | 4.2x higher on MI325X |
| FP32 | 163.4 TFLOPS | 19.5 TFLOPS | 8.4x higher on MI325X |
| FP64 | 81.7 TFLOPS | 9.7 TFLOPS | 8.4x higher on MI325X |
| Platform | |||
| Interconnect | Infinity Fabric 896 GB/s | NVLink 600 GB/s | 49% higher on MI325X |
| Board power | 1,000 W | 300 W | 3.3x higher on MI325X |
| Released | Q4 2024 | Q2 2020 | 4 years newer on MI325X |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP16BF16TF32FP32FP64INT4INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI325X datasheet and A100 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 | A100 |
|---|---|---|
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 | -- |
Jarvislabs
India
|
-- | $0.89 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $1.07 /GPU/hr On-demand |
Thunder Compute
USA
|
-- | $1.09 /GPU/hr On-demand |
Hyperstack
UK
|
-- | $1.35 /GPU/hr On-demand PCIe |
Massed Compute
USA
|
-- | $1.35 /GPU/hr On-demand |
Spheron
Singapore
|
-- | $1.43 /GPU/hr On-demand PCIe |
Packet·ai
USA
|
-- | $1.43 /GPU/hr On-demand |
Oblivus
USA
|
-- | $1.47 /GPU/hr On-demand PCIe |
5 providers list the MI325X and 46 the A100. Every listing is on the MI325X page and the A100 page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI325X was last updated on Sept. 14, 2026, and for Nvidia A100 on Sept. 14, 2026.