AMD MI250
vs
Nvidia K80
Two data center GPUs, one CDNA2 and one Kepler: 128 GB HBM2e against 12 GB GDDR5, 13x the memory bandwidth on the MI250, and Infinity Fabric 400 GB/s on the MI250 where the K80 is PCIe only.
At a glance
Memory
- MI250
- 128 GB
- K80
- 12 GB
11x more on MI250
Memory bandwidth
- MI250
- 3,200 GB/s
- K80
- 240 GB/s
13x higher on MI250
Cheapest on-demand
- MI250
- --
- K80
- $0.90 /GPU/hr
MI250 is not sold on demand
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI250 | K80 | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | -- /GPU/hr from $0.90 | |
| Reserved | -- /GPU/hr from $1.30 (12 mo) | -- /GPU/hr from $0.04 (24 mo) |
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 reserved on the MI250 and on-demand and reserved on the K80: 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
MI250 vs K80 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI250 | K80 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 128 GB HBM2e | 12 GB GDDR5 | 11x more on MI250 |
| Bandwidth | 3,200 GB/s | 240 GB/s | 13x higher on MI250 |
| Bus width | 8,192-bit | 384-bit | 21x wider on MI250 |
| Compute · dense | |||
| FP16 / BF16 | 362.1 TFLOPS | Not supported | MI250 only |
| INT8 | 362.1 TOPS | Not supported | MI250 only |
| FP32 | 90.5 TFLOPS | 4.4 TFLOPS | 21x higher on MI250 |
| FP64 | 45.3 TFLOPS | 1.5 TFLOPS | 31x higher on MI250 |
| Platform | |||
| Interconnect | Infinity Fabric 400 GB/s | PCIe only | Infinity Fabric on MI250 only |
| Board power | 500 W | 150 W | 3.3x higher on MI250 |
| Released | Q4 2021 | Q4 2014 | 7 years newer on MI250 |
| Precision | |||
| Supported formats | FP16BF16FP32FP64INT4INT8 | FP32FP64 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI250 datasheet and K80 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI250 /GPU/hr | K80 /GPU/hr |
|---|---|---|
Cirrascale
|
Reserved (12mo) $1.30 | -- |
AWS
|
-- | On-Demand $0.90 |
Database Mart
|
-- | Reserved (24mo) $0.0447 |
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI250 was last updated on Sept. 7, 2026, and for Nvidia K80 on Sept. 7, 2026.