The A4000 is newer, with 33% more memory and 87% more bandwidth, and is cheaper right now.
At a glance
Memory
33% more on A4000
- A4000
- 16 GB
- K80
- 12 GB
Memory bandwidth
87% higher on A4000
- A4000
- 448 GB/s
- K80
- 240 GB/s
Cheapest on-demand
87% cheaper on A4000
- A4000
- $0.12 /GPU/hr
- K80
- $0.90 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A4000 | K80 | Difference |
|---|---|---|---|
| On-demand | $0.21 /GPU/hr from $0.12 | -- /GPU/hr from $0.90 | |
| Reserved | $0.25 /GPU/hr from $0.11 | -- /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 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
A4000 vs K80 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A4000 | K80 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 16 GB GDDR6 | 12 GB GDDR5 | 33% more on A4000 |
| Bandwidth | 448 GB/s | 240 GB/s | 87% higher on A4000 |
| Bus width | 256-bit | 384-bit | 50% wider on K80 |
| Compute · dense | |||
| FP16 / BF16 | 76.7 TFLOPS | Not supported | A4000 only |
| FP32 | 19.2 TFLOPS | 4.4 TFLOPS | 4.4x higher on A4000 |
| FP64 | Not supported | 1.5 TFLOPS | K80 only |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 140 W | 150 W | 7% higher on K80 |
| Released | Q2 2021 | Q4 2014 | 6 years newer on A4000 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP32FP64 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A4000 datasheet and K80 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 | A4000 | K80 |
|---|---|---|
GPU.ai
UAE
|
$0.12 /GPU/hr On-demand | -- |
Sesterce
France
|
$0.17 /GPU/hr On-demand | -- |
Spheron
Singapore
|
$0.17 /GPU/hr On-demand PCIe | -- |
Runcrate
USA
|
$0.20 /GPU/hr On-demand PCIe | -- |
EmpirioLabs AI
USA
|
$0.25 /GPU/hr On-demand | -- |
TensorDock
Distributed
|
$0.21 /GPU/hr On-demand | -- |
Paperspace
USA
|
$0.76 /GPU/hr On-demand | -- |
Hyperstack
UK
|
$0.11 /GPU/hr Reserved | -- |
AWS
USA
|
-- | $0.90 /GPU/hr On-demand |
Database Mart
USA
|
-- | $0.0447 /GPU/hr Reserved |
12 providers list the A4000 and 2 the K80. Every listing is on the A4000 page and the K80 page.
Similar GPUs
Other comparisons in the same class.
-
-
Nvidia RTX 4000 Ada
20 GB GDDR6 · 20% less bandwidth than the A4000
On-demand from $0.52 /GPU/hr -
-
Our data for Nvidia A4000 was last updated on Sept. 14, 2026, and for Nvidia K80 on Sept. 14, 2026.