AMD MI325X
vs
Nvidia A16
The MI325X is newer, with 16x the memory and 30x the bandwidth. The A16 is cheaper right now.
At a glance
Memory
16x more on MI325X
- MI325X
- 256 GB
- A16
- 16 GB
Memory bandwidth
30x higher on MI325X
- MI325X
- 6,000 GB/s
- A16
- 200 GB/s
Cheapest on-demand
95% cheaper on A16
- MI325X
- $2.25 /GPU/hr
- A16
- $0.11 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI325X | A16 | Difference |
|---|---|---|---|
| On-demand | $3.06 /GPU/hr from $2.25 | -- /GPU/hr from $0.11 | |
| Reserved | $1.95 /GPU/hr from $1.48 (12 mo) | No reserved listings | |
| Spot | Sold out | -- /GPU/hr from $0.07 |
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 on-demand and spot on the A16: 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 A16 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI325X | A16 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 256 GB HBM3e | 16 GB GDDR6 | 16x more on MI325X |
| Bandwidth | 6,000 GB/s | 200 GB/s | 30x higher on MI325X |
| Bus width | 8,192-bit | 128-bit | 64x wider on MI325X |
| Compute · dense | |||
| FP8 | 2,614.9 TFLOPS | Not supported | MI325X only |
| FP16 / BF16 | 1,307.4 TFLOPS | 17.9 TFLOPS | 73x higher on MI325X |
| INT8 | 2,614.9 TOPS | 35.9 TOPS | 73x higher on MI325X |
| FP32 | 163.4 TFLOPS | 4.5 TFLOPS | 36x 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 |
| Released | Q4 2024 | Q2 2021 | 4 years newer on MI325X |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI325X datasheet and A16 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | MI325X | A16 |
|---|---|---|
Vultr
USA
|
$2.00 /GPU/hr Spot | $0.47 /GPU/hr On-demand |
Bentaus
USA
|
$2.25 /GPU/hr On-demand | -- |
Cyfuture AI
India
|
$3.00 /GPU/hr On-demand | -- |
DigitalOcean
USA
|
$3.80 /GPU/hr On-demand | -- |
TensorWave
USA
|
$2.25 /GPU/hr Custom OAM | -- |
Vast.ai
USA
|
-- | $0.11 /GPU/hr On-demand |
Sesterce
France
|
-- | $0.56 /GPU/hr On-demand |
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 44% less bandwidth than the MI325X
From $1.30 /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
-
Nvidia L4
24 GB GDDR6 · 50% more bandwidth than the A16
From $0.27 /GPU/hr Compare
-
Nvidia T4
16 GB GDDR6 · 50% more bandwidth than the A16
From $0.15 /GPU/hr Compare
Our data for AMD MI325X was last updated on Sept. 14, 2026, and for Nvidia A16 on Sept. 14, 2026.