A data center GPU against a workstation card on the Ampere architecture: 80 GB HBM2e against 16 GB GDDR6, 4.3x the memory bandwidth on the A100, and NVLink 600 GB/s on the A100 where the A4000 is PCIe only.
At a glance
Updated 5 minutes ago- Memory
- 80 GB
- HBM2e · 40 GB on SXM, PCIe
- Memory bandwidth
- 1.94 TB/s
- 2,039 GB/s on SXM · 1,555 GB/s on SXM, PCIe
- From
- $0.40 /GPU/hr
- 44 providers
- Memory
- 16 GB
- GDDR6
- Memory bandwidth
- 448 GB/s
- From
- $0.09 /GPU/hr
- 13 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | A100 | A4000 | Difference |
|---|---|---|---|
| On-demand | $0.40 | $0.09 | 4.6x more expensive on A100 |
| Spot | $0.29 | $0.08 | 3.7x more expensive on A100 |
| Reserved | $0.62 | $0.06 | 10x more expensive on A100 |
| Median | $1.79 | $0.16 | 11x more expensive on A100 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
A100 vs A4000 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A100 | A4000 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM2e 40 GB on SXM, PCIe | 16 GB GDDR6 | 5x more on A100 |
| Bandwidth | 1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe | 448 GB/s | 4.3x higher on A100 |
| Bus width | 5,120-bit | 256-bit | 20x wider on A100 |
| Compute · dense | |||
| FP16 / BF16 | 312 TFLOPS | 76.7 TFLOPS | 4.1x higher on A100 |
| INT8 | 624 TOPS | ||
| FP32 | 19.5 TFLOPS | 19.2 TFLOPS | Within 5% |
| FP64 | 9.7 TFLOPS | Not supported | A100 only |
| Platform | |||
| Interconnect | NVLink 600 GB/s | PCIe only | NVLink on A100 only |
| Board power | 300 W | 140 W | 2.1x higher on A100 |
| Released | Q2 2020 | Q2 2021 | 11 months newer on A4000 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32FP64INT4INT8 | FP16BF16TF32FP32INT4INT8 | |
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: A100 datasheet and A4000 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | A100 /GPU/hr | A4000 /GPU/hr |
|---|---|---|
Vast.ai
|
On-Demand $0.40 | On-Demand $0.09 |
GPU.ai
|
On-Demand $0.54 | On-Demand $0.10 |
Sesterce
|
On-Demand $1.49 | On-Demand $0.16 |
Runpod
|
On-Demand $1.00 | -- |
Thunder Compute
|
On-Demand $1.09 | -- |
Lium
|
On-Demand $1.23 | -- |
Massed Compute
|
On-Demand $1.35 | -- |
Packet·ai
|
On-Demand $1.43 | -- |
Spheron
|
-- | On-Demand $0.16 |
Runcrate
|
-- | On-Demand $0.16 |
EmpirioLabs AI
|
-- | On-Demand $0.25 |
Hyperstack
|
-- | On-Demand $0.15 |
TensorDock
|
-- | On-Demand $0.21 |
44 providers list the A100 and 13 the A4000. Every listing is on the A100 page and the A4000 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A100 was last updated on Sept. 7, 2026, and for Nvidia A4000 on Sept. 7, 2026.