AMD MI325X
vs
Nvidia RTX 5080
A data center GPU against a consumer card, one CDNA 3 and one Blackwell: 256 GB HBM3e against 16 GB GDDR7, 6.2x the memory bandwidth on the MI325X, and Infinity Fabric 896 GB/s on the MI325X where the RTX 5080 is PCIe only.
At a glance
Updated 5 minutes ago- Memory
- 256 GB
- HBM3e
- Memory bandwidth
- 6.00 TB/s
- From
- $2.25 /GPU/hr
- 5 providers
- Memory
- 16 GB
- GDDR7
- Memory bandwidth
- 960 GB/s
- From
- $0.12 /GPU/hr
- 5 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | MI325X | RTX 5080 | Difference |
|---|---|---|---|
| On-demand | $2.25 | $0.12 | 19x more expensive on MI325X |
| Spot | No spot listings | $0.14 | |
| Reserved | $1.48 | No reserved listings | |
| Median | $3.07 | $0.31 | 9.9x more expensive on MI325X |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
MI325X vs RTX 5080 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI325X | RTX 5080 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 256 GB HBM3e | 16 GB GDDR7 | 16x more on MI325X |
| Bandwidth | 6,000 GB/s | 960 GB/s | 6.2x higher on MI325X |
| Bus width | 8,192-bit | 256-bit | 32x wider on MI325X |
| Compute · dense | |||
| FP4 | Not supported | 900.4 TFLOPS | RTX 5080 only |
| FP8 | 2,614.9 TFLOPS | 225.1 TFLOPS | 12x higher on MI325X |
| FP16 / BF16 | 1,307.4 TFLOPS | 112.6 TFLOPS | 12x higher on MI325X |
| INT8 | 2,614.9 TOPS | 450.2 TOPS | 5.8x higher on MI325X |
| FP32 | 163.4 TFLOPS | 56.3 TFLOPS | 2.9x 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 | 360 W | 2.8x higher on MI325X |
| Released | Q4 2024 | Q1 2025 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI325X datasheet and RTX 5080 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI325X /GPU/hr | RTX 5080 /GPU/hr |
|---|---|---|
Bentaus
|
On-Demand $2.25 | -- |
Cyfuture AI
|
On-Demand $3.02 | -- |
DigitalOcean
|
On-Demand $3.80 | -- |
TensorWave
|
Custom $2.25 | -- |
Vultr
|
Spot $2.00 | -- |
Theta EdgeCloud
|
-- | On-Demand $0.12 |
Vast.ai
|
-- | On-Demand $0.16 |
Runpod
|
-- | On-Demand $0.39 |
Salad
|
-- | On-Demand $0.42 |
SwissGPU
|
-- | On-Demand $0.31 |
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI325X was last updated on Sept. 7, 2026, and for Nvidia RTX 5080 on Sept. 7, 2026.